sglang 0.4.6.post4__py3-none-any.whl → 0.4.7__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- sglang/bench_offline_throughput.py +16 -10
- sglang/bench_one_batch.py +5 -4
- sglang/bench_one_batch_server.py +86 -22
- sglang/bench_serving.py +197 -110
- sglang/compile_deep_gemm.py +4 -4
- sglang/lang/backend/runtime_endpoint.py +24 -1
- sglang/profiler.py +167 -0
- sglang/srt/_custom_ops.py +34 -0
- sglang/srt/configs/internvl.py +8 -12
- sglang/srt/configs/model_config.py +66 -29
- sglang/srt/constrained/base_grammar_backend.py +5 -2
- sglang/srt/constrained/llguidance_backend.py +9 -8
- sglang/srt/constrained/outlines_backend.py +5 -4
- sglang/srt/constrained/xgrammar_backend.py +18 -18
- sglang/srt/conversation.py +47 -9
- sglang/srt/custom_op.py +38 -3
- sglang/srt/debug_utils.py +74 -0
- sglang/srt/disaggregation/common/__init__.py +1 -0
- sglang/srt/disaggregation/common/conn.py +407 -0
- sglang/srt/disaggregation/decode.py +187 -134
- sglang/srt/disaggregation/decode_schedule_batch_mixin.py +142 -0
- sglang/srt/disaggregation/fake/conn.py +4 -13
- sglang/srt/disaggregation/kv_events.py +412 -0
- sglang/srt/disaggregation/launch_lb.py +140 -0
- sglang/srt/disaggregation/mini_lb.py +84 -70
- sglang/srt/disaggregation/mooncake/conn.py +441 -140
- sglang/srt/disaggregation/mooncake/transfer_engine.py +31 -14
- sglang/srt/disaggregation/nixl/conn.py +124 -442
- sglang/srt/disaggregation/prefill.py +128 -44
- sglang/srt/disaggregation/utils.py +154 -6
- sglang/srt/distributed/device_communicators/pymscclpp.py +315 -0
- sglang/srt/distributed/parallel_state.py +52 -5
- sglang/srt/distributed/utils.py +3 -3
- sglang/srt/entrypoints/EngineBase.py +11 -0
- sglang/srt/entrypoints/engine.py +129 -12
- sglang/srt/entrypoints/http_server.py +21 -6
- sglang/srt/entrypoints/http_server_engine.py +5 -2
- sglang/srt/function_call/base_format_detector.py +302 -0
- sglang/srt/function_call/core_types.py +34 -0
- sglang/srt/function_call/deepseekv3_detector.py +205 -0
- sglang/srt/function_call/ebnf_composer.py +248 -0
- sglang/srt/function_call/function_call_parser.py +202 -0
- sglang/srt/function_call/llama32_detector.py +93 -0
- sglang/srt/function_call/mistral_detector.py +131 -0
- sglang/srt/function_call/pythonic_detector.py +229 -0
- sglang/srt/function_call/qwen25_detector.py +121 -0
- sglang/srt/function_call/utils.py +52 -0
- sglang/srt/hf_transformers_utils.py +50 -7
- sglang/srt/layers/attention/aiter_backend.py +878 -0
- sglang/srt/layers/attention/base_attn_backend.py +4 -0
- sglang/srt/layers/attention/cutlass_mla_backend.py +2 -19
- sglang/srt/layers/attention/flashattention_backend.py +166 -35
- sglang/srt/layers/attention/flashinfer_backend.py +45 -1
- sglang/srt/layers/attention/flashinfer_mla_backend.py +45 -5
- sglang/srt/layers/attention/flashmla_backend.py +340 -78
- sglang/srt/layers/attention/intel_amx_backend.py +128 -0
- sglang/srt/layers/attention/tbo_backend.py +232 -0
- sglang/srt/layers/attention/torch_native_backend.py +3 -0
- sglang/srt/layers/attention/triton_backend.py +247 -5
- sglang/srt/layers/attention/triton_ops/extend_attention.py +12 -4
- sglang/srt/layers/attention/utils.py +2 -2
- sglang/srt/layers/attention/vision.py +1 -1
- sglang/srt/layers/communicator.py +517 -0
- sglang/srt/layers/dp_attention.py +6 -15
- sglang/srt/layers/layernorm.py +30 -19
- sglang/srt/layers/moe/cutlass_moe.py +370 -0
- sglang/srt/layers/moe/cutlass_moe_params.py +169 -0
- sglang/srt/layers/moe/ep_moe/kernels.py +60 -17
- sglang/srt/layers/moe/ep_moe/layer.py +195 -87
- sglang/srt/layers/moe/ep_moe/token_dispatcher.py +88 -8
- sglang/srt/layers/moe/fused_moe_native.py +4 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +220 -25
- sglang/srt/layers/moe/fused_moe_triton/layer.py +48 -4
- sglang/srt/layers/moe/topk.py +107 -24
- sglang/srt/layers/multimodal.py +70 -0
- sglang/srt/layers/quantization/__init__.py +10 -4
- sglang/srt/layers/quantization/blockwise_int8.py +3 -0
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +5 -0
- sglang/srt/layers/quantization/deep_gemm.py +60 -59
- sglang/srt/layers/quantization/fp8.py +113 -18
- sglang/srt/layers/quantization/fp8_kernel.py +118 -66
- sglang/srt/layers/quantization/fp8_utils.py +165 -43
- sglang/srt/layers/quantization/gptq.py +298 -6
- sglang/srt/layers/quantization/int8_kernel.py +18 -5
- sglang/srt/layers/quantization/modelopt_quant.py +334 -7
- sglang/srt/layers/quantization/moe_wna16.py +3 -0
- sglang/srt/layers/quantization/qoq.py +244 -0
- sglang/srt/layers/quantization/w8a8_fp8.py +3 -0
- sglang/srt/layers/quantization/w8a8_int8.py +3 -0
- sglang/srt/layers/rotary_embedding.py +6 -12
- sglang/srt/layers/sampler.py +80 -79
- sglang/srt/layers/utils.py +6 -0
- sglang/srt/lora/layers.py +12 -15
- sglang/srt/lora/lora.py +49 -5
- sglang/srt/lora/lora_manager.py +20 -8
- sglang/srt/lora/mem_pool.py +24 -16
- sglang/srt/lora/utils.py +17 -13
- sglang/srt/managers/data_parallel_controller.py +13 -5
- sglang/srt/managers/eplb_algorithms/__init__.py +63 -0
- sglang/srt/managers/eplb_algorithms/deepseek.py +223 -0
- sglang/srt/managers/eplb_algorithms/deepseek_vec.py +276 -0
- sglang/srt/managers/eplb_manager.py +96 -0
- sglang/srt/managers/expert_distribution.py +878 -56
- sglang/srt/managers/expert_location.py +448 -0
- sglang/srt/managers/expert_location_dispatch.py +108 -0
- sglang/srt/managers/io_struct.py +29 -5
- sglang/srt/managers/mm_utils.py +355 -151
- sglang/srt/managers/multimodal_processors/base_processor.py +299 -42
- sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py +6 -1
- sglang/srt/managers/multimodal_processors/gemma3.py +15 -17
- sglang/srt/managers/multimodal_processors/internvl.py +18 -5
- sglang/srt/managers/multimodal_processors/janus_pro.py +7 -1
- sglang/srt/managers/multimodal_processors/kimi_vl.py +14 -32
- sglang/srt/managers/multimodal_processors/llava.py +3 -3
- sglang/srt/managers/multimodal_processors/minicpm.py +27 -32
- sglang/srt/managers/multimodal_processors/mllama4.py +6 -0
- sglang/srt/managers/multimodal_processors/phi4mm.py +87 -0
- sglang/srt/managers/multimodal_processors/pixtral.py +9 -9
- sglang/srt/managers/multimodal_processors/qwen_vl.py +35 -35
- sglang/srt/managers/schedule_batch.py +185 -55
- sglang/srt/managers/schedule_policy.py +4 -5
- sglang/srt/managers/scheduler.py +389 -154
- sglang/srt/managers/session_controller.py +1 -1
- sglang/srt/managers/tokenizer_manager.py +231 -39
- sglang/srt/managers/utils.py +0 -4
- sglang/srt/mem_cache/base_prefix_cache.py +3 -0
- sglang/srt/mem_cache/chunk_cache.py +3 -1
- sglang/srt/mem_cache/hiradix_cache.py +4 -4
- sglang/srt/mem_cache/memory_pool.py +74 -52
- sglang/srt/mem_cache/multimodal_cache.py +45 -0
- sglang/srt/mem_cache/radix_cache.py +58 -5
- sglang/srt/metrics/collector.py +11 -2
- sglang/srt/mm_utils.py +10 -0
- sglang/srt/model_executor/cuda_graph_runner.py +87 -65
- sglang/srt/model_executor/expert_location_updater.py +557 -0
- sglang/srt/model_executor/forward_batch_info.py +39 -14
- sglang/srt/model_executor/model_runner.py +231 -101
- sglang/srt/model_loader/loader.py +10 -6
- sglang/srt/model_loader/utils.py +67 -1
- sglang/srt/models/clip.py +5 -1
- sglang/srt/models/deepseek_nextn.py +1 -1
- sglang/srt/models/deepseek_v2.py +732 -403
- sglang/srt/models/exaone.py +8 -3
- sglang/srt/models/gemma3_causal.py +7 -0
- sglang/srt/models/gemma3_mm.py +75 -33
- sglang/srt/models/idefics2.py +342 -0
- sglang/srt/models/kimi_vl.py +4 -4
- sglang/srt/models/llama.py +1 -1
- sglang/srt/models/llama4.py +10 -2
- sglang/srt/models/llava.py +26 -18
- sglang/srt/models/mimo_mtp.py +220 -0
- sglang/srt/models/minicpmo.py +7 -17
- sglang/srt/models/minicpmv.py +3 -295
- sglang/srt/models/mistral.py +71 -1
- sglang/srt/models/mllama.py +3 -3
- sglang/srt/models/phi4mm.py +512 -0
- sglang/srt/models/qwen2.py +133 -35
- sglang/srt/models/qwen2_5_vl.py +5 -3
- sglang/srt/models/qwen2_eagle.py +4 -1
- sglang/srt/models/qwen2_moe.py +206 -69
- sglang/srt/models/qwen2_vl.py +3 -3
- sglang/srt/models/qwen3.py +92 -19
- sglang/srt/models/qwen3_moe.py +457 -55
- sglang/srt/models/registry.py +9 -1
- sglang/srt/models/siglip.py +294 -0
- sglang/srt/models/transformers.py +291 -0
- sglang/srt/openai_api/adapter.py +114 -40
- sglang/srt/openai_api/protocol.py +37 -2
- sglang/srt/openai_api/utils.py +172 -0
- sglang/srt/operations.py +189 -0
- sglang/srt/operations_strategy.py +207 -0
- sglang/srt/sampling/sampling_batch_info.py +13 -1
- sglang/srt/sampling/sampling_params.py +2 -1
- sglang/srt/server_args.py +235 -38
- sglang/srt/speculative/build_eagle_tree.py +8 -8
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +8 -11
- sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py +253 -0
- sglang/srt/speculative/eagle_utils.py +181 -90
- sglang/srt/speculative/eagle_worker.py +146 -21
- sglang/srt/two_batch_overlap.py +635 -0
- sglang/srt/utils.py +197 -19
- sglang/test/runners.py +16 -7
- sglang/test/send_one.py +4 -0
- sglang/test/test_cutlass_moe.py +278 -0
- sglang/test/test_fp4_moe.py +248 -0
- sglang/test/test_utils.py +81 -42
- sglang/utils.py +2 -2
- sglang/version.py +1 -1
- {sglang-0.4.6.post4.dist-info → sglang-0.4.7.dist-info}/METADATA +31 -19
- sglang-0.4.7.dist-info/RECORD +699 -0
- {sglang-0.4.6.post4.dist-info → sglang-0.4.7.dist-info}/WHEEL +1 -1
- sglang/srt/function_call_parser.py +0 -858
- sglang/srt/platforms/interface.py +0 -371
- sglang-0.4.6.post4.dist-info/RECORD +0 -646
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json → triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json → triton_3_1_0/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json → triton_3_1_0/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json → triton_3_1_0/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json → triton_3_1_0/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json → triton_3_1_0/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=144,N=512,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=144,N=512,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=16,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=1024,device_name=NVIDIA_H200.json → triton_3_1_0/E=16,N=1024,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json → triton_3_1_0/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json → triton_3_1_0/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json → triton_3_1_0/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=16,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json → triton_3_1_0/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json → triton_3_1_0/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json → triton_3_1_0/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json → triton_3_1_0/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json → triton_3_1_0/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json → triton_3_1_0/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=20,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=20,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=24,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=24,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json → triton_3_1_0/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json → triton_3_1_0/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=128,device_name=NVIDIA_H20,block_shape=[128, 128].json → triton_3_1_0/E=256,N=128,device_name=NVIDIA_H20,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json → triton_3_1_0/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json → triton_3_1_0/E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json → triton_3_1_0/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=64,N=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json → triton_3_1_0/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=1280,device_name=NVIDIA_H200.json → triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=2560,device_name=NVIDIA_H200.json → triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=320,device_name=NVIDIA_H200.json → triton_3_1_0/E=64,N=320,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_1_0/E=64,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json → triton_3_1_0/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json → triton_3_1_0/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=64,N=640,device_name=NVIDIA_H200.json → triton_3_1_0/E=64,N=640,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=14336,device_name=AMD_Instinct_MI300X.json → triton_3_1_0/E=8,N=14336,device_name=AMD_Instinct_MI300X.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=14336,device_name=AMD_Instinct_MI325X.json → triton_3_1_0/E=8,N=14336,device_name=AMD_Instinct_MI325X.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=14336,device_name=AMD_Radeon_Graphics.json → triton_3_1_0/E=8,N=14336,device_name=AMD_Radeon_Graphics.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=14336,device_name=NVIDIA_H200.json → triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=1792,device_name=AMD_Instinct_MI300X.json → triton_3_1_0/E=8,N=1792,device_name=AMD_Instinct_MI300X.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=1792,device_name=AMD_Instinct_MI325X.json → triton_3_1_0/E=8,N=1792,device_name=AMD_Instinct_MI325X.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=1792,device_name=AMD_Radeon_Graphics.json → triton_3_1_0/E=8,N=1792,device_name=AMD_Radeon_Graphics.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json → triton_3_1_0/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=1792,device_name=NVIDIA_H200.json → triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=2048,device_name=NVIDIA_H200.json → triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=AMD_Instinct_MI300X.json → triton_3_1_0/E=8,N=3584,device_name=AMD_Instinct_MI300X.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=AMD_Instinct_MI325X.json → triton_3_1_0/E=8,N=3584,device_name=AMD_Instinct_MI325X.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=AMD_Radeon_Graphics.json → triton_3_1_0/E=8,N=3584,device_name=AMD_Radeon_Graphics.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json → triton_3_1_0/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=NVIDIA_H200.json → triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=3584,device_name=NVIDIA_L40S.json → triton_3_1_0/E=8,N=3584,device_name=NVIDIA_L40S.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=4096,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=4096,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=4096,device_name=NVIDIA_H200.json → triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=7168,device_name=AMD_Instinct_MI300X.json → triton_3_1_0/E=8,N=7168,device_name=AMD_Instinct_MI300X.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=7168,device_name=AMD_Instinct_MI325X.json → triton_3_1_0/E=8,N=7168,device_name=AMD_Instinct_MI325X.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=7168,device_name=AMD_Radeon_Graphics.json → triton_3_1_0/E=8,N=7168,device_name=AMD_Radeon_Graphics.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json → triton_3_1_0/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=7168,device_name=NVIDIA_H200.json → triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json → triton_3_1_0/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=192,device_name=NVIDIA_A800-SXM4-80GB.json → triton_3_2_0/E=128,N=192,device_name=NVIDIA_A800-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_2_0/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=192,device_name=NVIDIA_H20.json → triton_3_2_0/E=128,N=192,device_name=NVIDIA_H20.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=192,device_name=NVIDIA_H200.json → triton_3_2_0/E=128,N=192,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_2_0/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_2_0/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=384,device_name=NVIDIA_H20.json → triton_3_2_0/E=128,N=384,device_name=NVIDIA_H20.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_2_0/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=384,device_name=NVIDIA_H200.json → triton_3_2_0/E=128,N=384,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_2_0/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=768,device_name=NVIDIA_A800-SXM4-80GB.json → triton_3_2_0/E=128,N=768,device_name=NVIDIA_A800-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=768,device_name=NVIDIA_H100_80GB_HBM3.json → triton_3_2_0/E=128,N=768,device_name=NVIDIA_H100_80GB_HBM3.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_2_0/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=768,device_name=NVIDIA_H20.json → triton_3_2_0/E=128,N=768,device_name=NVIDIA_H20.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_2_0/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=768,device_name=NVIDIA_H200.json → triton_3_2_0/E=128,N=768,device_name=NVIDIA_H200.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=128,N=96,device_name=NVIDIA_H20.json → triton_3_2_0/E=128,N=96,device_name=NVIDIA_H20.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json → triton_3_2_0/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_2_0/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_2_0/E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_2_0/E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json → triton_3_2_0/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_2_0/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_2_0/E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json → triton_3_2_0/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json} +0 -0
- /sglang/srt/layers/moe/fused_moe_triton/configs/{E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json → triton_3_2_0/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json} +0 -0
- /sglang/srt/models/{xiaomi_mimo.py → mimo.py} +0 -0
- {sglang-0.4.6.post4.dist-info → sglang-0.4.7.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.6.post4.dist-info → sglang-0.4.7.dist-info}/top_level.txt +0 -0
@@ -1,646 +0,0 @@
|
|
1
|
-
sglang/__init__.py,sha256=T-fZEjKP66Q1q3PB56oREs5U3zf6bL0fNcdIbW8jMhE,1652
|
2
|
-
sglang/api.py,sha256=vHiKBg8wwIdmrpnGclop5BzJ-1Q88emrlrfLwNCHg98,7010
|
3
|
-
sglang/bench_offline_throughput.py,sha256=G1lLm5F-ZE9HCb7tBi7GqhlZaDelgG4or4HgUSAD0sE,13877
|
4
|
-
sglang/bench_one_batch.py,sha256=4XysFhY3fbJmVXVaIAvwb0dx5TYTtO8ONAAzTFT-ixQ,19222
|
5
|
-
sglang/bench_one_batch_server.py,sha256=XJNBXYEuhU3vuSXJ2BRDAwlSPUmnC-gLCCJ1FSpuC9A,10894
|
6
|
-
sglang/bench_serving.py,sha256=JkPLvFxCax5EKw-0DSoGxuFte2loApCIW7fGI_MuWsI,62931
|
7
|
-
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
8
|
-
sglang/compile_deep_gemm.py,sha256=XaKt2M4BMSiV8gx3ERzX5YwwEoE7suvUqgoi_wYlNpQ,6211
|
9
|
-
sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
|
10
|
-
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
11
|
-
sglang/utils.py,sha256=6Zpzw96ZDrZcBAI-OFmWtKvXcLBVLiHok0B42pK3kKs,16160
|
12
|
-
sglang/version.py,sha256=Rr2NlJlI5ama66BpRjzDUs7DOzgB59i8o_MYW0YO2X8,28
|
13
|
-
sglang/eval/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
14
|
-
sglang/eval/loogle_eval.py,sha256=pRPVA4fxGmT3_oXvXnlNE-UlPrcQGLBJF-OSE9YWJXM,4336
|
15
|
-
sglang/lang/chat_template.py,sha256=HKlx7snSWFED8GKF5ex79sQrPWFw5TSXQM0_LsiD9Bc,20552
|
16
|
-
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
17
|
-
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
18
|
-
sglang/lang/interpreter.py,sha256=OH1SFCm4rUCPO32MTo8j5V2Z13Jic7_r1GQOP1-aHaw,33234
|
19
|
-
sglang/lang/ir.py,sha256=gssBGxqQEVJmjR_PqG2yah48AsInGaO3CmnQ2boJThc,18769
|
20
|
-
sglang/lang/tracer.py,sha256=ljBo9VZ0zVaGwzNk32qw21acyo60N0UjIjqBbT5a1WI,8175
|
21
|
-
sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
22
|
-
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
23
|
-
sglang/lang/backend/base_backend.py,sha256=tEutGCU5tni1xGlrIjAVvA9aflJBt2duKrIDzqabJWc,1975
|
24
|
-
sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThcY,2450
|
25
|
-
sglang/lang/backend/openai.py,sha256=YFs7pCDK6_DoYmjTa-vgDVdaeE4PYr7E-sIC1q7vAns,16422
|
26
|
-
sglang/lang/backend/runtime_endpoint.py,sha256=4pTG1TnOVTWBCh3rMhqL_NP2hsawG9xuPpuDuUFvD6A,16882
|
27
|
-
sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZpI,4827
|
28
|
-
sglang/srt/_custom_ops.py,sha256=L7NuEaRD_Q6Q54n0NZnLXgWZURbnn8Tkg4NQedE6zgA,3616
|
29
|
-
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
30
|
-
sglang/srt/code_completion_parser.py,sha256=vafJqdTTreD9kvCsoMuxP_fFmoue7pOA1ibI9KXg4mE,5405
|
31
|
-
sglang/srt/conversation.py,sha256=569K5QEjnZGF45GjFGVZfP1n8RqmpcwxuVbgWRNFyis,35295
|
32
|
-
sglang/srt/custom_op.py,sha256=J1PUcGaeJJjfAjp06BQsLpUkKyR1zsh9MvDiDlqqJsg,1129
|
33
|
-
sglang/srt/function_call_parser.py,sha256=W3ZBbYP1Eg5z70sc1-HVhT_b1TJg5oxZDuGOppgMrA8,33378
|
34
|
-
sglang/srt/hf_transformers_utils.py,sha256=97J396flSaelvOIn0zO8Ji3bvFWUiL2mhLgxnup-d-M,10054
|
35
|
-
sglang/srt/mm_utils.py,sha256=1ScBunw_x4W8ebM_AcJ62-1T2mfT8NlMJqdAhkF1lb0,12367
|
36
|
-
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
37
|
-
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
38
|
-
sglang/srt/reasoning_parser.py,sha256=lZN5b1TJp3EK2GzxcICQhp0tRQjQw3ROOrjRgQe6Bsc,6341
|
39
|
-
sglang/srt/server_args.py,sha256=gW3mDnnRqrtpZTZOmjeWPfdnDNr070tSpUMrl7Qlc_Y,59525
|
40
|
-
sglang/srt/torch_memory_saver_adapter.py,sha256=HYlgYJ2sgmjs2RSjU2KbCaXijRg3mTDZ0ZcCB5Bt6Ps,2211
|
41
|
-
sglang/srt/utils.py,sha256=8xEOCR2aw4InlcwrdIN9EFfR-1FU26T_VylU5FQJ4-s,66467
|
42
|
-
sglang/srt/warmup.py,sha256=FmJiYfjRr3X_eAe7ojQaPoN17LvHpjDmRWRnO-k86AQ,1469
|
43
|
-
sglang/srt/configs/__init__.py,sha256=8EcVRP95epZ49DxBa6LgKWt7eO3Qe7Hrr3V1c6HkMnY,553
|
44
|
-
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
45
|
-
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
46
|
-
sglang/srt/configs/deepseekvl2.py,sha256=X8Q2gm7og_Ylx6tbFXetusfIJIXjWY_YH_p90C67BTI,23397
|
47
|
-
sglang/srt/configs/device_config.py,sha256=kdwFrk5myAURxdp4rSr8ANpBpSJfuBDoT-kuCyuscRs,442
|
48
|
-
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
49
|
-
sglang/srt/configs/internvl.py,sha256=0wUu_ExziVaA6bJjJ6VKP1uFJOHlj6fVx6y5wLSqJvw,27722
|
50
|
-
sglang/srt/configs/janus_pro.py,sha256=Rrb7kQsNaUP-TiZrjNk8Lr1momFrql8ScEunnrH0_xM,19086
|
51
|
-
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
52
|
-
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
53
|
-
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
54
|
-
sglang/srt/configs/model_config.py,sha256=MONwgieC5BZ2fPq31a-xTTx-RzPu1OGUBaEkcpdFkjU,23896
|
55
|
-
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
56
|
-
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
57
|
-
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
58
|
-
sglang/srt/connector/redis.py,sha256=KoLLUSY4Lu9zUrRJy2yYdtf1yanTaS0bQP8V0t95DB0,2552
|
59
|
-
sglang/srt/connector/s3.py,sha256=hn5Ow9Y6ItS8RMJDwnTQe5QaiQ7HKMgiwggE9QnUewM,3743
|
60
|
-
sglang/srt/connector/utils.py,sha256=isTvxauz1_8no5MW6p8Bwj2H9mQkweaRO_RSwAPA7R8,983
|
61
|
-
sglang/srt/connector/serde/__init__.py,sha256=MvBJ7FBJtnou-AD-EdsCdAIDCcA8kWvUNuRViILVJ-0,718
|
62
|
-
sglang/srt/connector/serde/safe_serde.py,sha256=Iv_mFsDvk-cXuw0WTykBZ2yGxW0jb82DwVqC7r3RmAU,750
|
63
|
-
sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOUIhF0ZA,1004
|
64
|
-
sglang/srt/constrained/base_grammar_backend.py,sha256=c7EbA6o_OlZTeUPkTcMVR0lNkZiCUo8C7ra5z7DJork,6822
|
65
|
-
sglang/srt/constrained/llguidance_backend.py,sha256=FP_Mafzb034Q62v19NZsdDQQ2iSl-dfLvCFuB8BsFFA,6117
|
66
|
-
sglang/srt/constrained/outlines_backend.py,sha256=P0EE0OoaJmxas0hnPN8Xz9vtST0J8f-wzuTsDY0aA2w,6864
|
67
|
-
sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
|
68
|
-
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
69
|
-
sglang/srt/constrained/xgrammar_backend.py,sha256=FKWrMb1QSgtCTCyk6pQZ5NS-5T3M6dvdxN7OOPCYc8A,7837
|
70
|
-
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
71
|
-
sglang/srt/disaggregation/decode.py,sha256=WDaXASJn2cp35r6ySPDdm5oXXg-3kR714CXX5xG28fY,25378
|
72
|
-
sglang/srt/disaggregation/mini_lb.py,sha256=SROT_-_OdZSD3R7ar2g90vL5WX5Ijc-K99zz7ewWD7w,12389
|
73
|
-
sglang/srt/disaggregation/prefill.py,sha256=Sf8wRv7BDBv0QQTahXR5wMTCiqOddhymx7L7vQbswXE,15527
|
74
|
-
sglang/srt/disaggregation/utils.py,sha256=W3Fe_MwJrSxHC1eMZRkD7C09VWFKRwfoM9_XXY-n2s0,5054
|
75
|
-
sglang/srt/disaggregation/base/__init__.py,sha256=KR8xXoRCDAy2U623mfP6ujXu42m1_F9EiudjrKu2I_A,130
|
76
|
-
sglang/srt/disaggregation/base/conn.py,sha256=hEOuR6kXrc7fRSYE9RAH53DLGHGaCcYWod6IkmtNttg,2491
|
77
|
-
sglang/srt/disaggregation/fake/__init__.py,sha256=zmfeKYXjonRhfFOck1c_mP7Q4cW5G0f1RsTwRivKu0s,47
|
78
|
-
sglang/srt/disaggregation/fake/conn.py,sha256=N9y0ZBhfPkrhaKN3gsRxqb2wWpiioaANtFqO9wVl2Ec,2553
|
79
|
-
sglang/srt/disaggregation/mooncake/__init__.py,sha256=1vacEHmWjf7zgbMPzsXKB08FqNKNCquJdUiDlO41BOk,122
|
80
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=MF2N1FbBdI5mh5Btl6gkX6Dw8MqjKPMVe9NvwdspEdY,33652
|
81
|
-
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=MxDAB9ZetRF1pFS2LP3FVHPtQ1HjIt_SK3UMaYHZ94o,2604
|
82
|
-
sglang/srt/disaggregation/nixl/__init__.py,sha256=n9HjrRk36WUcZNeetGWOh2pSriLp7GNTq7YYX9K3EtY,85
|
83
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=ekYUmS2c9TnkFrzS1DYGXZG-Yrb5WbMIL6gnQHAxG8M,30104
|
84
|
-
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
85
|
-
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
86
|
-
sglang/srt/distributed/parallel_state.py,sha256=cCQq94H8A-rO2wZf_bCf1lkwcTVOBrHubM9K1PrzVSY,51560
|
87
|
-
sglang/srt/distributed/utils.py,sha256=U-BSaXYjWwnfG8g-tUfBhjKt5Ug097nyHtu3g3aea_Y,8473
|
88
|
-
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
89
|
-
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=qje-PQ3v8yaV-oYVLPws1mgIlXVsGKFCOvXHmSe8ZXg,19624
|
90
|
-
sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py,sha256=fLoptT_U0lVAqkhEg-ge53CdFSIKQpDRiqHYKwJVEZg,10974
|
91
|
-
sglang/srt/distributed/device_communicators/hpu_communicator.py,sha256=gPjEH1-izoby5uDrfUlzNf21luPT0Ow7pJjhCRKnHy8,1728
|
92
|
-
sglang/srt/distributed/device_communicators/npu_communicator.py,sha256=bRXN1Md_4SHQGzQYZa2GrHv2zbIU5vSpkueHiAZL1xQ,1345
|
93
|
-
sglang/srt/distributed/device_communicators/pynccl.py,sha256=obXyCaZznZHSt486XCnEOBNG3Cen7ysuuMuGRlTTl-8,10095
|
94
|
-
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6EMz-oPS9J16WHo2Q_SRL1DtlJKK63Hfg,15349
|
95
|
-
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=d8mykYmXM1lfbPm8GNtqCF0Un_pdXYjbNmsgoVFyyow,20874
|
96
|
-
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
97
|
-
sglang/srt/entrypoints/EngineBase.py,sha256=xoyvp6XAeDLY2_Q2Ng33H-fRhrXHv2ldJJKd-HuDhqE,1870
|
98
|
-
sglang/srt/entrypoints/engine.py,sha256=0L0jis9GLehFgkYP9cBBw7-Plg7e_quCF5OiX82O8io,24704
|
99
|
-
sglang/srt/entrypoints/http_server.py,sha256=xH-iXPx9wg2VqHW9dFxDAyIwcdBMAsUboK7MH4SR-5E,31003
|
100
|
-
sglang/srt/entrypoints/http_server_engine.py,sha256=ihA6y3GXRs28Y9U3SgdQcJQjnw_SVIby7QrVgiafX04,4846
|
101
|
-
sglang/srt/entrypoints/verl_engine.py,sha256=RYizNetTHzcB8dErX1EW4NsyRNGkFPljYaAf7pVRPdM,7002
|
102
|
-
sglang/srt/layers/activation.py,sha256=oSkdo8B8najXFcVay3Y__CEvgXh87lAIhG0CMp2Ugqs,5954
|
103
|
-
sglang/srt/layers/dp_attention.py,sha256=MwqjY3uOg4dKjFxTyNlWnnHaA0oLL3oUkapfh0qs1IE,9438
|
104
|
-
sglang/srt/layers/elementwise.py,sha256=XCrR2i-9dP-H6jQo2zUuquwZrsl_wEQqj5Wxk6WUf7o,13987
|
105
|
-
sglang/srt/layers/layernorm.py,sha256=kU47PX_V46RblaxxMNxWxGjWSa99o0w2s68908rGp6Q,5957
|
106
|
-
sglang/srt/layers/linear.py,sha256=nC9MxJrFap1BEyqgFlBySH4IeQruIbcBp32cOhUl5Fw,52149
|
107
|
-
sglang/srt/layers/logits_processor.py,sha256=eeG2zXZguvz2r1OVKVd5HFSPseL5fzRenh0cYuKO-GQ,25557
|
108
|
-
sglang/srt/layers/parameter.py,sha256=zqWyEzpWzP4NNTjq3G9khq6XofgpcmJqQLg6Vd4WyWE,15084
|
109
|
-
sglang/srt/layers/pooler.py,sha256=nR9F4x0GP2KYkJihhcL-TX30gfLY3mVhOLRfeBDeKL4,1942
|
110
|
-
sglang/srt/layers/radix_attention.py,sha256=F71GgDes_fEt_cHxR9HM2QhNG5u7uF4zDAuLqwLYEV4,3481
|
111
|
-
sglang/srt/layers/rotary_embedding.py,sha256=eVBwYvGpFhL1KyyPutQuZotmvSpChcxzyhpmcbQ6cKQ,48267
|
112
|
-
sglang/srt/layers/sampler.py,sha256=JmzceFPgl3vjaf9VQA3OPEW52tRZ_njrOxpGdZ35LP0,11261
|
113
|
-
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
114
|
-
sglang/srt/layers/utils.py,sha256=tkTz86DFZ4NRMEUc4QkYNskUskdxXoEqkWqaMGbhP7E,1045
|
115
|
-
sglang/srt/layers/vocab_parallel_embedding.py,sha256=GPKCQiR2yH5Z2XSE9g3vWObdegcwPnMHXv7qEZovLH4,22755
|
116
|
-
sglang/srt/layers/attention/base_attn_backend.py,sha256=lGujcYJ_CxHJy0Q9L6Phn3ds-nBGMy0OGj3R54R65iQ,3334
|
117
|
-
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=kCNn5Ub0jCsFjhVhuE-9qK53gu5a9oMStMeT2lcc6CU,9904
|
118
|
-
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
119
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=o9ggOpIAhmLzxRfVg8mjLM_x6vesOb5f6MayVZe0UJU,87868
|
120
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=53TXhmBpU5rs04-4u-yXclwJ5UYg7WJfyLDZJ8nSDOU,47651
|
121
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=4BJy18GHYiNVjcSkvmzxgoSk8nugsLrZuars_m-4oYw,32406
|
122
|
-
sglang/srt/layers/attention/flashmla_backend.py,sha256=wR0bkLz3mj5EfuHEi9fwEP2vtq6xFhsrIijpFb009o4,10340
|
123
|
-
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
124
|
-
sglang/srt/layers/attention/torch_native_backend.py,sha256=K5hUqBgakk2COSQqsaxWs0yEVOHS-7BlOygZTOeI8kE,9444
|
125
|
-
sglang/srt/layers/attention/triton_backend.py,sha256=oEEiUwHbm4rNw5ExbQ2c3n0TwAgkk77yuLFenj9bHOo,26902
|
126
|
-
sglang/srt/layers/attention/utils.py,sha256=3NyDQ2T2IHwFb5mAJzbpyxRYmdkB8htM3_9_U5GqQDY,2889
|
127
|
-
sglang/srt/layers/attention/vision.py,sha256=TOTRWzd5d_9fCR8DOvy_oY-vJ1zl2cVYni5hlZGDens,15355
|
128
|
-
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=DPu_aCPgwPqKWZPEQmp_xA7MPbpV2ip-MEICCB470Ao,19120
|
129
|
-
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
130
|
-
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=m12jEnQkNJguATqvZ57HtMC2hhU4wqdB8xAYdh25BxE,13922
|
131
|
-
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
132
|
-
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
133
|
-
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
134
|
-
sglang/srt/layers/moe/fused_moe_native.py,sha256=U0qh3udHuJJll3udydqABoXPFz0au9aEj8Lv7OAHYvQ,4655
|
135
|
-
sglang/srt/layers/moe/router.py,sha256=5Aeqoix_AS4uymb665OJE904wVSBkQeFdZP4e7KKPvg,10530
|
136
|
-
sglang/srt/layers/moe/topk.py,sha256=ir3CXINtE2xeLJDh9S3PlxikRC0e4AIxb-lEQqttnBk,11127
|
137
|
-
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
138
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=tj2yIWdgn3zaz9uuhsm6qx4syaX_t-zpYPLKotCX89k,33547
|
139
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=TPBcD9_To_sQhayur9nbQNRn8AYTCO3gXtytKHfUkGM,40349
|
140
|
-
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=y-t3qG0GS9r8GLTe6_-5BV43Sp5BPHIoveDlYFGIt7s,22051
|
141
|
-
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
|
142
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=mNFBkSB9n1axyLAs9dsIwdAj7L5w9ZFEEDsxOL6XPPE,55996
|
143
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=BMOV76fabrZcoyDmRpRbH11Jc0ogWH2k2QAQwvZIpgI,25084
|
144
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
145
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JJN0hryyLr5Zv3dSS7C8cPFhAwTT6XxUVnBGMZvV6JA,2752
|
146
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ouRyZ5PEMPP2njPftCNhs-1g1y6wueWLmhI7G1SjV1k,4131
|
147
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=dd4aQZ1afXaEGS3ZUH31Yc3maWhT4L61m22QTxjqBm8,4141
|
148
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=8GLZzOVJNpfOXXMQaMtvcpQICzPG3jDNARvH4PxHX-s,4134
|
149
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=s-7qBDx_J3mFu09Nk14ZVseGeX5GPNRStQjohRCYt6k,4147
|
150
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ypxsH-62Mw2Td6I8k6K8A52D9ORsUtwcBThhz-h7f2I,4150
|
151
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=2Z27aKdaA4VxqtICk-ft5Sc1HqRS87mN2ry7cXhCD9g,4131
|
152
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=yf33YmWlVSjjyg0Q4OMAWvc9gjRxvttMrQBUEOfPl4I,4153
|
153
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ZWMClYN1moVRUP2f0hYac38di_pUgZggyl9d2D5rnoc,4136
|
154
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=C65Q2Mv1LxFQ_qDnv11IZ9nwl7sGZo72nWDflMttu4g,4147
|
155
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=T-_T-oW4qpjTIBaGVxukJksRE7Yg8m9HNHgJ2XmR3aI,3242
|
156
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I3k416HbXU_rYb8scD8gAI4fuBlElHl06PM347Qa11w,3253
|
157
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H20.json",sha256=RgV8C4F1LO09h01YsgF_eqX6GNoBtC7ulPfJRUUbg_g,3241
|
158
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=192,device_name=NVIDIA_H200.json",sha256=nsNEuDNks0tVLfQfIm7xxFwEeptTfQcoa9fJy0NS8xQ,3247
|
159
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=R4gBc3sMY5QwOtcGwGKdk2Ak4UsUbBd3jDUeKKk0O1U,3257
|
160
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=qbqjisJ4oKmcYzumHPRk5UyOzsdi8J6xas82UWHMeAI,3263
|
161
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H20.json",sha256=vS2DRIDOqWyiBvbG6H746ownfkD1F8Aj2YZ0ET9xll8,3232
|
162
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=1n5XyZZ5sKAi-Z1duWOhLUfr6gkvnOpvxfbqIT6iU_4,3265
|
163
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=384,device_name=NVIDIA_H200.json",sha256=xqhl748it8GV2KXX0XixitE_ywnsKksqK8AGL7tAgT8,3254
|
164
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=FsWbV4Q6AzAtgegVuENBDz2ZcSJsqNiwUIVfQbpP7hQ,3244
|
165
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=T5rXJOZYNEs_3hE8g3ch802DnySbNiIqdn0s0RlJr8U,3249
|
166
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=9L5C8VcSsiUr5XryXB1AO3DknlAQowp6DU6S7OSzEA0,3248
|
167
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=IuvyC8TNhCVAmUZfLSoETsyCKsmejKXrs_0zuwFLPAU,3265
|
168
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H20.json",sha256=10Ntu2aVD5vGLonx-jW0qNw-tgZWdZmzMGx7utDVeng,3237
|
169
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=pdQ1RvXvdWDn8Y8-8MAX3vn-T-wbtkZvHV9GZZvNjnc,3266
|
170
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=768,device_name=NVIDIA_H200.json",sha256=JraM-Nvbg5V_TJkSl6UPFYZN1zHHoIbr2pAcksenoTY,3248
|
171
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=128,N=96,device_name=NVIDIA_H20.json",sha256=JtcHRlPz8xQEAqJ9EWI63oYvdmjQFG6VTHqtt85VOSA,3221
|
172
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=144,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=pk6VZChh2Y0CsJSzjtUhOnlta1QLTUEWy33aKQU47XY,3244
|
173
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=Gmk24hc5lVIfQtqSa5wLOcWKedMN8aZUe93DBh6J1AY,3249
|
174
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1024,device_name=NVIDIA_H200.json",sha256=uY_XMPomaXMXxIkTR4ctU_Ybri_jMv2VvCcV-f6O_bw,3255
|
175
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=pCCKkdUzzuBVtljyk7AEIAbeDf12DUiieXaODZXzm5E,3254
|
176
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=trX2-c4N6hTTD6zFNi6A2bT3FkhxKjkM2rPl-o1K9ss,3250
|
177
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I4d56uD7E1JMXD9RAxq3FebdPquDsnNEkVaIY9Ctm9w,3246
|
178
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=sqkPi4atVPAmx_Q7KuTqsvjLOIpnJzcL6yQRIvGsJS8,2752
|
179
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=0ejgnIQ_mzJhKjQpnT-I1Vj9-rPfGlTcQ8u0cXgekUw,2746
|
180
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=lU4fjngJmpzOafi-3_q0vj2pLfZQVVagFnZNoI97etk,4128
|
181
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=ilUf76TmbtaL3W0bara6JIBEiV_iPIs29UjLbH_GYtc,4145
|
182
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=4ye1VakIIzrGUTxGNb_DM5v59djLgok8SeBeU_YI6Go,3252
|
183
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=G4PKqWxh0MlBhg7QHKj0m--_fP3Ll0gs7VJaeg-NIDM,3254
|
184
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=bKX9AvcxN6k-i3RUmHSchZZ3rjoYRYb4iBqhCI4L3MY,3257
|
185
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=OeJUCPVBD1z9CSooZpy3hRyAasjKqFAQaTLcWK6PWno,2741
|
186
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=OiEXvxm5tmcbrEtSIWlS67x-4h96gDg31L3sPjShnEo,2750
|
187
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=cGVjKx34AJRE2LGY_JWwpwS5gBqD9_c9T3xe0pUMH9g,2914
|
188
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=cuw9Htez46GkPB8TPtCDiJGhGSpAfqA4-UmLy32WHFs,2739
|
189
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=Fo1glFnfnYQOqNvk8Kau2WP90iO6zTZ36iG9MrlbPU8,4150
|
190
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=xOQj9y9CQFRCRBZ8G9RHMw03PrCNybpcXRU5sME84-Y,2911
|
191
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=1YsFa5ID0jTHIxOGpkt8VeDzhF9LpyATfQry_ikSDVw,2748
|
192
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=FGVvsvw23DeDFLj7TNqm402fAtib2cPGRZR3ePBeUp4,2753
|
193
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=kklgf2qLI5CQYiJJ5e9Gxx2gAfGxcyMDYpdJnIXPV8E,2748
|
194
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=8e0tN_DHPwvh_HECVHx9oOF_4WWdaht4s6Nmd_K-aBU,2904
|
195
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=fRzKfVFIcnxqu6DvGJQNltuFRRGz8F-eaL73bIzBzo8,3255
|
196
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=20,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=zq1x3KwZ3YuzE42OPPsElXT_VS9sK135CdB1RsotLU4,3252
|
197
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=24,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=lJbEa7VsBVKL_iRoHniB-2nceMrPctkqtjKszPnX4pk,3248
|
198
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=RuUDK9XfgXs1eZESWQR9ba4tu-rCRG_UCYwjaJ568sI,3264
|
199
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json",sha256=wlCi9aoYp7Zc1GThEutvWDbse0kKnNaQgFJsd_L8be0,3259
|
200
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=tPYxeo_xUOkjQrZMdf9v4IaFrw0RGaZNLGLJPOhjE_g,3260
|
201
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=MW7KzNa7DcKm53u2Jh-mnb93A3ICefgQHkdKONJMfew,3255
|
202
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=0aSYzpv_cBAlpWCPrfGgNTCfae1KdKQnT56E8XFQl7A,3262
|
203
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,block_shape=[128, 128].json",sha256=JEOXj48phwoumZWBwNq9TpqxVwIrbnfot4QfAdzvLJI,3249
|
204
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Lqom_VMIPduSZTZQdeL2Wl_x3r9q6RmI9bojJrYwQZ4,3255
|
205
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=XmKFaMheq7NNrsvYCJteul0w809l_l460ZiDQC9ToGs,3262
|
206
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=5ro9O8Nf-7MB8NGCQ3QV5kB2k3iSWe0rdTz2A4W72CA,3732
|
207
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=5ro9O8Nf-7MB8NGCQ3QV5kB2k3iSWe0rdTz2A4W72CA,3732
|
208
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=23CJv3de1UDX3EduMpylD9AA8qL5kzMSjLK4GDMqlro,3734
|
209
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=IMTKnPRjhSptf7smIkpqmMjSML9SQ7I8CpkbR3Inzqk,3258
|
210
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=yJzHX8nNWnKwj9M8281dwwPhOHQ039mBpvNgG7poy3Q,3264
|
211
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=R4B2n2vGt4pPo6jS4Bmnx8AYtcfF9qQJE5bD7OhmXHs,3265
|
212
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=Y4WpmVGlGERHoeoQNGkQ-GC-MsEtMblqnAVuDbARJdw,3240
|
213
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json",sha256=RUkd9fW9WbajF_fFIzppsE1qyWGR5aRC4Cln-BPdu28,3254
|
214
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json",sha256=Sc9xK1wtRUqIzXppbutcq-Y2e9M0DZl2OGVzzB0aQuI,3265
|
215
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=7YmtaXKnmX8DdYnUJ7WQFa7xjr2Yun9WIdQNoCf_K28,3255
|
216
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=8gNamin6OqMiQ-LMVe4yQBo9ONioiC4loSWPnKcS1XI,3262
|
217
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=3Zt4hbC3yJxWvP0T7K93YAPaUP8fQ1P1Wk0CGqtBga8,3259
|
218
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=P8GpVR8fjrX7OFbBBFE4y4MJ4uhgoyUV4NYCm1qhWxk,3266
|
219
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=4B0SmzRQ2-PsBJcFe7neM1OKfWpsbiY4x6c6COQNMsQ,3254
|
220
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=XyiOCufhAu5BCMHoW9q4gLSRQEGd22bJnJkw15MqFYg,3267
|
221
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=f5HTi_9fWvInEyJp8pFgaVN6A9vxu3_845eSZGN9Ypo,3264
|
222
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=Piw4LN6d8QYrUahWsw3XUOtTMD1o3vHPwA94sGI56Gk,3242
|
223
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=3T8_rF2PEojhgTMyQ8DscXgJCWWdWfDPj4M434zWcA4,3243
|
224
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=TBscr1uWwpY0FrKQ5Y3EO_Qg6I97u4f_zjnWRvoeLvE,3260
|
225
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=6QPLhZurIqcMVdy3w0Dd7gLViKxsyJRBz-qd8agpi6Q,3248
|
226
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=uv-RwTNZT2n264dLo4eWxUpB3g7QqUyf2MFEGiRvoqQ,3251
|
227
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=XbCRIOmiNqVKh89p-0UxvvspINRDA1iV83f9l5yORwA,3254
|
228
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=4uQnjGPWokscrxiXDIvexOA8OkK5vkoIulmvvMFIEog,3250
|
229
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=i5AXj26mWI-xEoOnLCZDXUzz8jk2RjDcGuaiT1QYSbY,3263
|
230
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H200.json",sha256=fJKk5LEM_LSnq1yc3ekLqAfbUWzPojQA6yX3XgSFo-o,3254
|
231
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=iJVlnCYTNDMb6U1UnV46ZuL_8LcpOv_XFaYWIeRFeNA,3263
|
232
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=KfvSYCMG48vnRb35d9WOxYyZulI-RBrUGXUHQxXi4hk,3264
|
233
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H200.json",sha256=60yuOluuk6q88Ze0toPJB8hzMBvF7ZWyMZpriMdQf3g,3252
|
234
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=DA4PrCu_BNLSWWVTwOicNfbyqUNW7BTZC2dyFz9DVbU,3265
|
235
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=prj-QxdfS9Ns5WRPvahY_Tr7CyqlaVgNHPT89SS5zzg,3239
|
236
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=AUgoHK1PmAFehSNmsbxunlBdzM50Q5nFvdnG9FSOjOw,3265
|
237
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H200.json",sha256=pC5fdtEFc5aVNzpj_REHhz1QPrGvgI9iQCvlodDP7J8,3244
|
238
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=yZ_6KgwJvKPGblpbHPQvEMcUc9F7G9A0mSXHfgfztgo,3263
|
239
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=oxOKFDrgmw1YmgxTtRa1uoe3p09ylTLrkj_jOTqNh1Q,3249
|
240
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=bfr70r6PmM95w7raabQOaOOSPiwU2OQCOZh-kKXIehY,3248
|
241
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=4g9lABUJnB-iVwXfYPYcI05XFPG4jY8o0yJUK7kSPZM,3253
|
242
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=RGLqrAGvPCFZ0jMPBCJ0TqsnrSdW-EbUaSZu61cWGN8,3265
|
243
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=sjEVPVTgUAlp4s8tZLGSyeNzbW6zTtUm2IioH3nZsIg,3254
|
244
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=eD3Y9sOwHFcgVdOfya8KxPhvLx_b4whfEWm4d8Y2HW8,3268
|
245
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H200.json",sha256=KIfpZydSl31FOEqq0EBfxTyWRj1QTDwTjkPHFjNO3_A,3253
|
246
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json",sha256=Hh3sfBOR5j3Hz9O2yoOw56A8KAYZabqWTr1uXem4vvs,4733
|
247
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json",sha256=Hh3sfBOR5j3Hz9O2yoOw56A8KAYZabqWTr1uXem4vvs,4733
|
248
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Radeon_Graphics.json",sha256=Hh3sfBOR5j3Hz9O2yoOw56A8KAYZabqWTr1uXem4vvs,4733
|
249
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=V_sgDtEtGEuBsGVa0maYJHhhGqe1NE7l-1ek2ed9WP8,3082
|
250
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=LD4Z5MRR5Ivi4bYB5hMgymtvmFyVJwq6gmehA7fzecc,3271
|
251
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H200.json",sha256=GLIH4egg-pE-NWU5XqKuJCoRXciHN6GSc3NaE4PaeYg,3261
|
252
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json",sha256=zcNvXyWveWBefuCTviItdnkFAUi3ou30PHpkktwodQM,4730
|
253
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json",sha256=zcNvXyWveWBefuCTviItdnkFAUi3ou30PHpkktwodQM,4730
|
254
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Radeon_Graphics.json",sha256=zcNvXyWveWBefuCTviItdnkFAUi3ou30PHpkktwodQM,4730
|
255
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=AffDc0_51ML8HiA3757zbD10TZJdUsUDIYIqO4g0yUw,3250
|
256
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=IEYBNjt9HGnzoOVSWvL0A0jUqq926QD0_BvVYR4RA1Y,3252
|
257
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=Ns9Y12aZbJnFhcG3nwb67bDqqiQAo9tdTAIe8K2Ajz4,3255
|
258
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=obNtHlqs6l6EBqGm0e0TD2wR9TYoQV_N9Y7om847WJk,3268
|
259
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H200.json",sha256=juxJYeWYFHeLb-83_IDgrHEpoeSEursjXD43mTHBdLE,3246
|
260
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=HOxWmCI2ifHmWc0or2y8nEen86jDeLDov1-tuMzuhxo,3256
|
261
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=csHezh0HGWaNwrblGzMgcE95hqbqjWS8HImLRJYr_ts,3266
|
262
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=_5weLBinQCDzyV75hHKIT95Y0ce94KWft2_5BC6EkbQ,3254
|
263
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=4O4VeMpgFNrqWyWqWgYgcYAgBQnOlAXvt26CRSXK-sY,3270
|
264
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H200.json",sha256=qfjbXqbl902TuiyzzomUy2sMvs-Dud8ZphDRY5WIPBM,3260
|
265
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json",sha256=ZnslvT6HljcanWwYjF8nthwqr_h4tjyb_wELBdcGD48,4732
|
266
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json",sha256=ZnslvT6HljcanWwYjF8nthwqr_h4tjyb_wELBdcGD48,4732
|
267
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Radeon_Graphics.json",sha256=ZnslvT6HljcanWwYjF8nthwqr_h4tjyb_wELBdcGD48,4732
|
268
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=Ru460ZgnUP4U8OsJfwF8n-AI-gfcolNR3_qzoxG6DtY,3254
|
269
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=K6BGrKw_oHTAtHjsZldcjp-BUM1dIecKXrrRn9OpRGs,3254
|
270
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=4Q_-yITMfijOMoguUM2n96clARh-DUFsS-4oW_a3Jpc,3252
|
271
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=qqFoMaObuO8pFWcSb9q0wYsdC4eSCO7B-_ruQhR1N9M,3264
|
272
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=-5nkLIunjG1ghPoUEtt2AXEQw9oGiilP7K3UvQv9CqE,3252
|
273
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=BXjSVGdvgP_-7xTvbHOO6ZrXWe0qSXiQChxoHGgWL7o,3263
|
274
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H200.json",sha256=Pi2coJlJlpgqXiPRd77B_eCmmi7sCdBuoSGK1RA5YO8,3258
|
275
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_L40S.json",sha256=p2qlRhTt7owWB8keEmoCrPZpo39IAxsKnULFQ7R38SI,3873
|
276
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=hdWYpkBWfG9kwUYco1VNjwU_S65Coat1uzfEJl33UfY,4409
|
277
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=hdWYpkBWfG9kwUYco1VNjwU_S65Coat1uzfEJl33UfY,4409
|
278
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json",sha256=hdWYpkBWfG9kwUYco1VNjwU_S65Coat1uzfEJl33UfY,4409
|
279
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=DxYu8regZOSFu8ugFGA_QbwWK4g8xwQUZF9a_nNY4Cs,3255
|
280
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=obzfE_9XgsbFNfC9biYOHxR-V_Bgc7PKT8qZZJaiJJc,3262
|
281
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=qwKy8oaMsd3QrXgQbM_x9xcfYiHK_Ou1CEwDPL5Gbgo,3259
|
282
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=rR8b-OuQ3watb8b2zuNlxKDSZpzlAagm9nb-FdKkt7s,3270
|
283
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200.json",sha256=8G_QqV_DhvZ6xSavMSpeE6qcXPVpsVjEtJabydybKqY,3263
|
284
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json",sha256=hW48t9J7ptdtil6MKMSfXV-HQ8Eba3SLOgScNuwseSg,4733
|
285
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json",sha256=hW48t9J7ptdtil6MKMSfXV-HQ8Eba3SLOgScNuwseSg,4733
|
286
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Radeon_Graphics.json",sha256=hW48t9J7ptdtil6MKMSfXV-HQ8Eba3SLOgScNuwseSg,4733
|
287
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=BAJnXTZoewwCtzJLUPJ0oYuALv640MvDuLseGcsYaaw,3252
|
288
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=-Tj7ImS6ZFDof_0VTyq7kVm8XD9B54RD6CUOPSf3Jjg,3265
|
289
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
|
290
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=3YQakSmUKhpw1KO7Hn-tEc-yyD1fEj01_6JlSYnrrlI,3274
|
291
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200.json",sha256=W2ka_U8pzwjzX62NEGKXR32uuSR_zfHD1XjXYf5bgBs,3262
|
292
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=-RzUWSIAAsg6iA-8SPMa68hPpBVoUyMJs3dLP7edRu0,4323
|
293
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=-RzUWSIAAsg6iA-8SPMa68hPpBVoUyMJs3dLP7edRu0,4323
|
294
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json",sha256=-RzUWSIAAsg6iA-8SPMa68hPpBVoUyMJs3dLP7edRu0,4323
|
295
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=sY2nWMPh9lsIkhPCjkHO245wpnfFbrHmzdcZDVFPVww,3265
|
296
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Uz5X80VcNBOaxshwVNUEittHk2zqB4HQCfTJ4TPG5aM,3274
|
297
|
-
sglang/srt/layers/quantization/__init__.py,sha256=0qQgvF5wR9VlYO9xv8GERPgtKWZ9OMilaxcSUeGTyN8,12424
|
298
|
-
sglang/srt/layers/quantization/awq.py,sha256=KemDG55U3B6YZVjMV71awVAIj0islFvtxcUHmOBeGy0,6739
|
299
|
-
sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
|
300
|
-
sglang/srt/layers/quantization/blockwise_int8.py,sha256=BgPrsTakDDFirALkW9q9VmFk0wFZv9cotkTU69Gnxeo,15122
|
301
|
-
sglang/srt/layers/quantization/deep_gemm.py,sha256=a8T2IdWV11m4tnXfSwEmNzb_LwdaXcuaseFRsR07TtM,13124
|
302
|
-
sglang/srt/layers/quantization/fp8.py,sha256=QguTeY-PMgU5Vu3QdeqmS3DgFD1R9avwgBZABG92dcg,40709
|
303
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=OKpebbn09CpRzxFgB-RB_I4ZnWGLJ9nR0YTFu6-ZMdw,32570
|
304
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=VHU7glWyKjAMvR-zXAvZIuqMk6V3fj-rOx9K3xR-LEE,20075
|
305
|
-
sglang/srt/layers/quantization/gptq.py,sha256=gyGMOPXHzozK7pPWSjKgLdFX9h7MCEww7n8FqEVEVac,15364
|
306
|
-
sglang/srt/layers/quantization/int8_kernel.py,sha256=W9sXTIs46LJQPHLCt6UjoAVkIZhUn5eWq8pbyQBHpSo,12163
|
307
|
-
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
308
|
-
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
309
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=TpPgtbV7O5r1JY4Wm0np2pReQO6XERIdEDQcV41oTn0,16596
|
310
|
-
sglang/srt/layers/quantization/moe_wna16.py,sha256=KtFr4lIslMA12yx4JjXXPOsa5OHjxXWA6scYCRQnFMQ,19483
|
311
|
-
sglang/srt/layers/quantization/utils.py,sha256=AXvGD8KRZVVrkRR1Y64fGkz4lkUP-CAjAQdp0LDNXrE,5266
|
312
|
-
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=UFwlch8qEm2J4muM4hMATj06-rf-__lSbBqVr00j1tc,11459
|
313
|
-
sglang/srt/layers/quantization/w8a8_int8.py,sha256=MkvmcxQj3X5AZbx8pgnHYAikc_Xd_jOhJXaxx7255ho,8984
|
314
|
-
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
315
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=EaOKuIA0zXwqmH_eVhWeNdGJT9d1d9gVvFyYkgpdjDg,25665
|
316
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=cGckgXOZQGMv7VIVQeXYblvHKUFC8hLpQfwNb18rj7E,26191
|
317
|
-
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
318
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
319
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
320
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=-iq634sU38yWFA-h3w-B4kTALeXMo7uRZQI6CckMZTo,5494
|
321
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=SkeQYXW5i6M3ZLp867KFwQXVBcIPAcdYFILUTY0A850,5934
|
322
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=RdHQxWXwXqvio31192vsLaKjEr4f_DjpMPKlarY1IAk,3251
|
323
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=0vLaJgo5B9ti-XMFKJuvSoMGjsZQ-RhHSx4cC8Xji-U,3254
|
324
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=tkLjwLC_aVXhzuvo-2QHkojXZauPJsf3jNHFn1S7uRA,3244
|
325
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=CPo1WRF0HgsQMPBkvpoImElQMrfwpJLhEvL86e6fkPU,3247
|
326
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=9qdyh6ki9LAyq7VDO9WMRmBOPWKSrZhU-I7z1E9bTKA,550
|
327
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=xqJNygFgPCe4jDpkfVOWCXpuNMUjmssdD8oGhp2iXv8,3726
|
328
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=xqJNygFgPCe4jDpkfVOWCXpuNMUjmssdD8oGhp2iXv8,3726
|
329
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=9ya9f1Nt0g0RD-6sRRBZOaIPLSpSFZCz7jNvqTPrgFE,3732
|
330
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=3E-LXaW1FPoTiCPBurm7U2SV4KmWi4xmqwdCjHvZkkA,3250
|
331
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=aO874ivXpnr7WrFUC7CCN4hxxc_IzOTw2SYNv6L0-2Q,3252
|
332
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Qoj9rLLRDbKM4IKBCXvN8RcxzSmNPd0TQUiM7CXDqHI,3241
|
333
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=UZljnxxCSjwnZlX3OgKWZJGXCf5BWF_agEpNX8I4Zxc,3248
|
334
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=4D3Ku4y7BCVEJzueKvQC_KvOR026w3ONWsxfsA_YrEc,3249
|
335
|
-
"sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=6POXzQZHdNwcBDv1w6BJKbLMRDt0jbFUuMsMNf-ToEs,549
|
336
|
-
"sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=1G2RuKNS88mjD76ZhXFwR-LBhKaqltupGVJQdhsKwJo,3250
|
337
|
-
"sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=0DXL6DllcvdsF7roLYpE5_7JmBEjcTWiFw2iHjEUURs,3255
|
338
|
-
"sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=7v4tp0RaT4vxF4urSBrkK5FR_5ikeFQ1htF3DwDl1lk,3249
|
339
|
-
"sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=3matoCzEe4aexwoe7YTmkjyE4NA8khWXjL5EySuNwzA,3254
|
340
|
-
"sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=0J2MFgaLkv-mfVE5x363lgVKYU6miLG_xRO3tJUga_M,3249
|
341
|
-
"sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=JeXNLkbMAjdDKV-WpzQy87SXN06towo3xUofLtvYCQI,551
|
342
|
-
"sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=k81ilt1195nP4r197W7cZonPJ5f2Z5AtSwUZjG2nMOE,3243
|
343
|
-
"sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=_vkouDwGIPyydiFA2Vx8S9MK5ULFUGs3SwrIPaLhxH8,3252
|
344
|
-
"sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=4ubbhwSFX_XbefRLEkLoWxJkcetFWPzsszPu0X3_Wrw,3242
|
345
|
-
"sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=9f8Ib4gLEFSfdNpO8IL8uiONImvqnlPbJrZ0HM3OB-o,3247
|
346
|
-
"sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=FhyniGTx5QeCuVrBSVTQys6q05Pr5lPEcPykpAX7Iyo,3247
|
347
|
-
"sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Boa83ZSPZ0LvzqtfLGvois5QK4TmJfwjA2n96c9ET58,549
|
348
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=I6a5wQ0R3cBp8ix_PDamWZN2aJmV_1p0tg430L3Updg,3727
|
349
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=I6a5wQ0R3cBp8ix_PDamWZN2aJmV_1p0tg430L3Updg,3727
|
350
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=I6a5wQ0R3cBp8ix_PDamWZN2aJmV_1p0tg430L3Updg,3727
|
351
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=fmbzpCd0iyVAjrnUkALmq_RkwuzV_VnaplbS1Mj_csk,3261
|
352
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=wY8Pt8_57OLIvyELktqNe0G1p5GEwVUacZ3xEebGnLM,3262
|
353
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=0v17v78pETXv6S2ZoibekxOVhiTmCm807DYG4DONUck,3259
|
354
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=I44PvJj758-sw_fCOVROLTpG0NQ5_5PCYyQcpZC1YSY,3259
|
355
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=tG5_iVeRBHTgHX-liOf79nWRjj_lUZ-NQWTbBrBgORQ,3246
|
356
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=DBCxmR29Qf9f78DPcZN4t_Ybr43TALNZT6F5vAP-56I,3255
|
357
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=-CVHqClROli9FWe_FnlnuAG2LiFivDFK_nghH6t-BWc,3261
|
358
|
-
"sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=9tCZxJ0eAD7AYMH7OqS3AGppJUllKnJLNvMq7FMXdsA,552
|
359
|
-
"sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=smT1Yg8fVLAzRqQubCCxirWJ9KLbwEqCt9vP_doPv_o,3246
|
360
|
-
"sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=dTe1O3UiXScsLUSZo4Gij4Q5Ae7IlL3DSnMPiZTY02Y,3250
|
361
|
-
"sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=GsLoYkaZ2p4Qu0Coj-X90s7JWyfZBOloIHPlyNKSIes,3246
|
362
|
-
"sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=BpKweY4HfBx5xvqSvwNahy9x7R5FH-YK8j6rLFQdKwo,3248
|
363
|
-
"sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=QMVfMXS0Yjgob8_9xps1xuZi6KnY5l2MeKxXLRjTeg4,548
|
364
|
-
"sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=I6a5wQ0R3cBp8ix_PDamWZN2aJmV_1p0tg430L3Updg,3727
|
365
|
-
"sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=I6a5wQ0R3cBp8ix_PDamWZN2aJmV_1p0tg430L3Updg,3727
|
366
|
-
"sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=bSxTaptdcgj27mQGmdUmQtYTn4V_8EcmtRaVNigKjLA,3730
|
367
|
-
"sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=8zuJhFdd6aXREpiqPFhIKEFWA5lgLVGrG0-a9UXcBqk,3262
|
368
|
-
"sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=inXXq68RP540fgLC5HI3gWM5fRZvuCQ_1M3nWdVZB04,3249
|
369
|
-
"sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Zn1TvhAoPOv0zQBYHOZhwdDw3oqyxm0zIa7IJkTCHpo,3247
|
370
|
-
"sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=yqjO7zML7EseBJw6Bn5MTyHeAitkPsl1dndXeL6Rn6A,3257
|
371
|
-
"sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=-nQIhKAOVCQrxLV6HDlcD0V8HMWvqrv-vyiORVU7qls,3244
|
372
|
-
"sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=Jhs4odx25fgXyXSmnvbmNZWypv99ouhdBDJKD3drVBo,3249
|
373
|
-
"sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=M3nwpZd2-0w263ywZt9gaw53z7MN673T5tl4tc43Ntk,3249
|
374
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=6HvsrapGzLyCAZe_NE0VdcJTSJv1aztD1ZqFG7VODUA,3729
|
375
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=6HvsrapGzLyCAZe_NE0VdcJTSJv1aztD1ZqFG7VODUA,3729
|
376
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=6HvsrapGzLyCAZe_NE0VdcJTSJv1aztD1ZqFG7VODUA,3729
|
377
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=7PaawDEmgCGOKnf5l8oVoCEWx9l6APn25ndZ8Yrtar4,3257
|
378
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=upLDyGsriavtW-C0uTZ2AhctVUDzxv_5XV4rwIyctec,3264
|
379
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=vLoV3JMtvHOKpR5D1BeCQPMuYlWUAlrXu54gByNkwKY,3266
|
380
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Mtw7a9BSspj2TzC-aPxE82o1LEvwzgbUuIofwRxUNA0,3263
|
381
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=B0lo3SuoQXhBEnojH2TwpVeurvlKD8yI8kQrJ5ORhWU,3249
|
382
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=5V84G_NyEFd4o8cL4y34MPWY7UqxL54cQ-79rayc684,3252
|
383
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=NHdx3tZnfLF7NplswMzcTRbQEQFLtChg4rd7GU9lMbM,3262
|
384
|
-
"sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=ZYZ03ziPGwG2sCasEYLj7ZIP7vNO8UNBR5qNTmKgRMs,549
|
385
|
-
"sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=laYeH4w0iZOj2Yg3vDgtKoroNQnwBEX4GUGLrO9095I,3260
|
386
|
-
"sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=TWcPDZ2miQMD6OWDC1FteRs80ND9RC-oJL3PLVmJbtI,3257
|
387
|
-
"sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=6HvsrapGzLyCAZe_NE0VdcJTSJv1aztD1ZqFG7VODUA,3729
|
388
|
-
"sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=6HvsrapGzLyCAZe_NE0VdcJTSJv1aztD1ZqFG7VODUA,3729
|
389
|
-
"sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=xxNfGtHAlxDVX7PBnqExJN0UnYlA0UbaYoXUmuX0JsI,3739
|
390
|
-
"sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=6Z7kIa14RjVq3ek_C15q5mUu1IrY2r0OP8S-_pm-MYU,3252
|
391
|
-
"sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=r63SZkUJJV87B00hAX074_uaC7wwQXdurlJsB1jUA0I,3254
|
392
|
-
"sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=bVJlejBgHjRWPDbv-5kbkz1nHjpUL6VKctg3LG1HcVI,3253
|
393
|
-
"sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=xBhxdCFf3waTUsLxJxA54R90zODbC_DKI3XXBVKjKRw,3252
|
394
|
-
"sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=XGNbUYyeRnb5NyfpTc1lueHjW_i49O9j9MA-MorasdI,3726
|
395
|
-
"sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=XGNbUYyeRnb5NyfpTc1lueHjW_i49O9j9MA-MorasdI,3726
|
396
|
-
"sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=16Qk4BrbVQOdR9Et2T3SnLphQdvEwuuG3W3XCmAFa3s,3734
|
397
|
-
"sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=O_SV2vo_oaABfT6Mxqcmo12pnhKtfX4TnXfe02OcHJk,3254
|
398
|
-
"sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=g12Xkurat7oUS7LdS9pHLKFlur4_FaMGiGBvdq-iBCs,3242
|
399
|
-
"sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=JcpVETWcbX4uPmaOzswLLlaWqQtOfOkMQxniAqMZZGE,3245
|
400
|
-
"sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=tFdrY5nADmXUlShdN8w8Jzkxuj_RPLXCRceX9FhQ35E,3251
|
401
|
-
"sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=YA4P3iWQcyvx9wRgvs5zOqj3MKb0i3lDTfX3iTzJh2c,3723
|
402
|
-
"sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=YA4P3iWQcyvx9wRgvs5zOqj3MKb0i3lDTfX3iTzJh2c,3723
|
403
|
-
"sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=m0E9TwfZjvtopYFhI92VSaqhiUZpjBu69kv56rKMEuQ,3729
|
404
|
-
"sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=TO2qRGmp37v53Zqu8Joeq_BSbtwM_mpVoozGyoNg0-o,3254
|
405
|
-
"sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=rumUJPNGutObsu4kunFhPa7BogfRiss2qCrQf1_iOm4,3248
|
406
|
-
"sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=0xquf00fgfrDODpaxyre0VDcjqfzqExj939rzeJ8pMo,3244
|
407
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=xsFMrq4aybClfJyhm78c1Hf1jcyFSGnfygdHYp7OhSQ,3727
|
408
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=xsFMrq4aybClfJyhm78c1Hf1jcyFSGnfygdHYp7OhSQ,3727
|
409
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=A4uzWJTNhyNVh7ntOvUpT0TheaEVu_js0NCNdav8mTs,3730
|
410
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=uh2HLUNRGIqNulVSJrhamvMo_uExHA-S2okQd6rHB8Y,3247
|
411
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=SXCT2-3lldJFBzSL4uk60UhGBrzV2zM34A2RkFXgXEs,3250
|
412
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=qG6v3n3qF6LE2DdGT-mDIXecZ1a7vg7p3QqXYCMX85k,3254
|
413
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=EgFTGyW_YuDwyEDUCoGglyI1ETdj9J7AR0UfJ86jMoI,3249
|
414
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=BpKweY4HfBx5xvqSvwNahy9x7R5FH-YK8j6rLFQdKwo,3248
|
415
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=lW8CYKL8FWEYfgoACK6rwLTKxAytO8eHgQPNRHbsI3w,3246
|
416
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=NiorJgOotxkQcP49ID3z5al1UA4QQDrT8MvbCwAWL5Y,3248
|
417
|
-
"sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=FcuzcmKFf2RbaUpAaAsuObUefcGMgNPMDbVdHXRkoGY,549
|
418
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=YKPb9yvuMTBy2mnelxrN0eYcufaMH1ZgNx7_0gGEROI,3259
|
419
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=aQVljEx0CzvgkWQz8kN89qm6Q-iQJDeK7dKrco9ooFI,3252
|
420
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=bPQWtvaJrzOOIgI-R-MIxs_f4yC_FobkDydu3OkOFtg,3252
|
421
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=h32lCTFilLlyKbMeuJvNWG1v0yJJzNj93kwSvlrHfaY,3249
|
422
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=ZRgiuHZ2SFC6u-WV5DGwau4k1RiPLI67eENO0e-5Ylg,3253
|
423
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=kjQ_kvF38bZGcmaeJGSJsSR0NcUjUOh3LZ2-5c4kPvE,550
|
424
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=DM908j7iJKK0eLDR8R2aBmZC_zmMjWc2LXxLktYtqAc,3254
|
425
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=t-maxasK-8kv32_gJWOK97QfQrsk3iXW81KGCaLm5HM,3260
|
426
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=-hP_P8NM0K04mGzTmpGBNibQ5xxh5gPz5WtoMXhoz1E,3253
|
427
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=0jX-z2lTgVw7ABLmWsIsQdqW4EjmbXKRDHye_XPLCAE,3245
|
428
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=FB5Le4obvPoCgFSnC_3-Uh59n-Mt4Rol8saXVcK3RPw,3252
|
429
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=mZGU39sobtUqNYKjtyIGjhOZyCOQFJMF3MinA1zjTJA,550
|
430
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=UkXzxGGVXuq3ymqaXb1QEqnqXcXBN-mFvZDZoKHH5kE,3258
|
431
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=tUvbbgl18cgbbmQQe2St-Of4wkhyC9QQOWgjVTBu_dQ,3255
|
432
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=kLviGvVngpgOuelfKtvv9Is7MWQ89rGxlomMRP6t0Ic,3250
|
433
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=_exM3wJ3FMmGHweBcH-8IxwZBzaOmPaF3ScMM6KDpiY,3253
|
434
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=ue2oWml2ouUTZelYx5Nt5pgCmY-ib3mLV1reJL9ZudE,550
|
435
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=sVbH4YRLTxBqvTh_6xbtXkj3orOrKytlwM-_4gtD6IY,3725
|
436
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=sVbH4YRLTxBqvTh_6xbtXkj3orOrKytlwM-_4gtD6IY,3725
|
437
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=sVbH4YRLTxBqvTh_6xbtXkj3orOrKytlwM-_4gtD6IY,3725
|
438
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=2t1lmnh4Fn67YSq4naP2g_RqYC0VtsVgTw5GS14A__w,3258
|
439
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=syb0tPwrdYUCOoB7fTEXES0GaJ6jy_IqI3i136zudb4,3260
|
440
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=vlys0Zi_CaaU41OHGbWSBtbVglFi98bgqEySBMc9Sdg,3258
|
441
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=YWyByOlKSqp5lbcUa8eu6N2dHRKJqJDbCDSjdDQJngg,3249
|
442
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=ENRWYdUwI0ooHb6IwcHliupRWOPnw-7-WtxZB-qQGJI,3245
|
443
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=7hTWsESTVJjC8xfGoLF5oZorEpncfrDGh6lXnLZhFIg,3248
|
444
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=j5PTW0IC4Z2yQIygcdICaOsvb639u6Mv-ZpJYkrBQ2k,3254
|
445
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Nv9KP_KLGsRJdJF755dZBvbTws37u1GM2UigMRlAtl0,552
|
446
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=v2VwGLYvrYy3Nfr7CiOksjaR-XbwHu21RsXZ3J6_yfI,3258
|
447
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=9vTtCCtEf7yhMsng-ZEAU_gvKMTq04wTgeykV0BgnTo,3262
|
448
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Ggy4hejkcWjiw5Bi-wGzSP5JLVuvOjip_rbjXFBJZbs,3257
|
449
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Xy4mgZx5iiEvuv2ydO4dFNIT8s0jgBhNHE1vu93fGJM,3250
|
450
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=TdWuE2RIsIyr4Im24MuWK3XyiNtbhO_hAiAXDz5gNUk,3246
|
451
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=nD-Ki3WuQ-MktvFHasYk8iC1syPUmfbpsocXUea9Bdw,3247
|
452
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=x476nFeltB_2iO9_6y-z2P_unAbh7ghLPFi5z2LOTOo,3253
|
453
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=ZOWEo__oUy8AhJiAlRCuGNAZNdNweFdWBFptJYkwxs8,552
|
454
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=sVbH4YRLTxBqvTh_6xbtXkj3orOrKytlwM-_4gtD6IY,3725
|
455
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=sVbH4YRLTxBqvTh_6xbtXkj3orOrKytlwM-_4gtD6IY,3725
|
456
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=sTvaJ0RiCaQem4F1z7oES6RVRJ2gKgBuccX13S1SqGc,3733
|
457
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=4uWiQMh3cZY_EtLA0a3PU8Z1VCunF2PpolTPYeP9Rjo,3256
|
458
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=D0moiKqS73oril32iNj5gRJUWpT2SZ5jf-ZesUZnNv4,3254
|
459
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=r-zndmVTFE-b1jnON9zwuBQvTBooVuj1qjf7hvjFEt8,3246
|
460
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=N37dUL_J2JVpgLFlnlz__Ck7Z4njROnNAO8V2oiDqr8,3253
|
461
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=zuSYO0DejuHJK0dqSszTySoZUFizgjtLIXSjjOC_lpc,3726
|
462
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=zuSYO0DejuHJK0dqSszTySoZUFizgjtLIXSjjOC_lpc,3726
|
463
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Rq-eMMK1deUJzmHQOH0E_pwQP7l-ZU-ECTP7Xwegavw,3736
|
464
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=LdtOyXsA9r18GiFkmDOkiRinsDSZBZ8NYapL59EZ4iM,3264
|
465
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=07GarBHmiiYkyqn-qxEtrAcgCETuUbqm6HqlbH9yJi8,3252
|
466
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=ZVFmEA61hieyp5xAyLTkzflAmWcuNtXYiAjlfAwMx7g,3253
|
467
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=kEuvCsW3YNByF-DALYqPZpW3TL8ZbtQ5gUNq7-8YvZ4,3252
|
468
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=aoq4792zPo87QO7VrEf9fb_vj0zPiHIu7Ho9aMXwcLw,3731
|
469
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=aoq4792zPo87QO7VrEf9fb_vj0zPiHIu7Ho9aMXwcLw,3731
|
470
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=_RHvFcbtpsZBKxZte2-E3SUHtL1pwRtqwhSV4BMcyKo,3734
|
471
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=PD4AJYCkHfy2ivv9baMouFXzBTy0eKMumbAfxfm91HI,3256
|
472
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=FImA-TJ_tQDjqwoNWxS--sRDoKDXf9gamlME3tkxH58,3252
|
473
|
-
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=FFBjSWlpKXMxfAUUYUqXbOK_Hd7qBeBsfbcaa9uB4qY,3249
|
474
|
-
sglang/srt/lora/layers.py,sha256=xdP2Gwlw9PCPZBhujGqO6aBn0eGxpVeIBFUp1LIGCto,13119
|
475
|
-
sglang/srt/lora/lora.py,sha256=uNvbjZ_Wr1SLI9-ElRJA_JKwkibSGroP5Bfpsr9MI-Y,7527
|
476
|
-
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
477
|
-
sglang/srt/lora/lora_manager.py,sha256=1vkfpx5EfkGji08xUFEBTNfeDjpjfieQDRScIbEmO3w,11528
|
478
|
-
sglang/srt/lora/mem_pool.py,sha256=dIx_8yZiJkFMyddfKL9G0zzgDxdkCQjG2qrbdHxqPtA,9633
|
479
|
-
sglang/srt/lora/utils.py,sha256=S53SOjYqeEc9toqGaThod9MNWEJs0OJew6KY558cMF0,5250
|
480
|
-
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
481
|
-
sglang/srt/lora/backend/flashinfer_backend.py,sha256=el6IAB4kTgDTbwCggmqFuukliyoapN5X6FLksG-4wJ8,4151
|
482
|
-
sglang/srt/lora/backend/triton_backend.py,sha256=uqwBGlguXX8EkCKjSPqac6SPTgcKA31u3u6HkKPQcos,2530
|
483
|
-
sglang/srt/lora/triton_ops/__init__.py,sha256=JGOYPIn1XbGcyJTbt8A0qoc02PYONSGNNjGkC8yJpAM,283
|
484
|
-
sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=vOUDzC_Sq7UGnDbdF8F7ChKG12hDIOFwwMb7e62Lz9w,5280
|
485
|
-
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=qCpJAksCSXS3Znm-ABx1QfrdNqj9hrP61oaeW-n2RhU,5945
|
486
|
-
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=yNBgl8jS76DPlGJg8puRkSnKkewf2_2oKfVZZRq4lYY,4351
|
487
|
-
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=EoF9HymgQ1V9DwyOJOvbw1hCbEjprVOne_fC4VHgj-s,4518
|
488
|
-
sglang/srt/managers/cache_controller.py,sha256=RDKuRuRdrMWhsy4QOXvtTG_u_NQUQFly7a6BnoEYiMY,18434
|
489
|
-
sglang/srt/managers/configure_logging.py,sha256=fOJaXAQ1n9m-8KPJndpsKvS885i69SMafoEADLIVfIM,1633
|
490
|
-
sglang/srt/managers/data_parallel_controller.py,sha256=nB4CD_g8VShTZHCQ9sfst73lQeSvOChFzeY-6RRAhL8,11648
|
491
|
-
sglang/srt/managers/detokenizer_manager.py,sha256=SpLxTsSPKBZfD-ZMhJ5zpPPGuUb8PmcYgFSL9CsurU4,10696
|
492
|
-
sglang/srt/managers/expert_distribution.py,sha256=r3o5RGI0gnV7xb60AApqKYa0oiSB37oB7hQBX7P3xZM,3225
|
493
|
-
sglang/srt/managers/io_struct.py,sha256=A6Odr-nyO3CJ0925m_2zCnvra6oQAFPU2o7F9TqSD70,31835
|
494
|
-
sglang/srt/managers/mm_utils.py,sha256=qTxNjMWdQwPpWBjk86eOS-UEgkfwNq5WwYiREK3wRso,18090
|
495
|
-
sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
|
496
|
-
sglang/srt/managers/schedule_batch.py,sha256=OhrWYd_ywWiNNMOp_fcDOIwYt9_gX7oZnR9imEXbkb4,67564
|
497
|
-
sglang/srt/managers/schedule_policy.py,sha256=mCgwmhCTpzQJawiNizIxjY4nszkxokMmMz9DlDGGUa8,19666
|
498
|
-
sglang/srt/managers/scheduler.py,sha256=2TzJU0DZ_nmLnYJjQGn_JZJdfG-cDQnuMZUrINiOwsU,91483
|
499
|
-
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=aaj0z1PD3fGIOPoTtWwqoKsii0yQCR7txVFXMPECveQ,29879
|
500
|
-
sglang/srt/managers/session_controller.py,sha256=o-ifit0n4_xHLNmyD0Ams8FxGRgxFybX-Vz1hwgr3UQ,5755
|
501
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=DMGNicPMCudO81ryP4zPC9GbO6cAkouGNUHtSQ4f_pQ,56162
|
502
|
-
sglang/srt/managers/tp_worker.py,sha256=cnI2JRxDqM7RXaaXAnLHNyYH4Jt7SB6HLAD5fRoWoNA,10025
|
503
|
-
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=W-FP7dkR9_voS0emMj4N5ML3Iao9gNZc-on6iUflbrw,9835
|
504
|
-
sglang/srt/managers/utils.py,sha256=5i75uLlQOF_5CaT02CrWtwozMTtwTg2_nLP8Dtr-JZQ,1536
|
505
|
-
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=DMeqUdxyOZ5IKo-Z2NjEteJS-Oz6gG9jyU27c8QwA5A,10367
|
506
|
-
sglang/srt/managers/multimodal_processors/clip.py,sha256=lRc2mcuDbAhZVf-0EfkO81pqDiol9zLvTpDqtPIBQ2k,1525
|
507
|
-
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=hpjpGFzlRBQ8Xv08i37X_VUhnDp_Qm2xD1_F17vK8fI,3253
|
508
|
-
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=G52ck_3UQGeyrtvjLqI8B0Tm8iNsyB_ahiMTAvx083U,2191
|
509
|
-
sglang/srt/managers/multimodal_processors/internvl.py,sha256=mydI4yWRMiIo6y8ZL_wxqU2IPpfVf2eR4SA-yOmK3H0,9172
|
510
|
-
sglang/srt/managers/multimodal_processors/janus_pro.py,sha256=UJoKQWsoU9kittKDwjWbG2KC12wSA-4A3DpTPhA6VoI,1854
|
511
|
-
sglang/srt/managers/multimodal_processors/kimi_vl.py,sha256=vC9OeS7gVTHzazbluiQ1I0QRKqszlqK75ghUA1rmUNc,2490
|
512
|
-
sglang/srt/managers/multimodal_processors/llava.py,sha256=APzkprLvqrQkFA6LoDemUa73FtjQL4lwGSnsx5R4vuk,8004
|
513
|
-
sglang/srt/managers/multimodal_processors/minicpm.py,sha256=uEnlsImjHBOMVNGlfBGpn1zCDLNeMY58HvJ7ZthL2N4,5698
|
514
|
-
sglang/srt/managers/multimodal_processors/mlama.py,sha256=MLiGS606LzVtdoXvjWGANx-K_7nE9J_fMVmkXN7Gz8k,1661
|
515
|
-
sglang/srt/managers/multimodal_processors/mllama4.py,sha256=50Yox7TaGrrB7iPjN1dQ_UzuY41x7VLmMcRXBhTgUvE,5592
|
516
|
-
sglang/srt/managers/multimodal_processors/pixtral.py,sha256=YG4-ufrooQnlGZ4gCnl-Scwor322oCHHbO6-SdztwpI,4064
|
517
|
-
sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=l94DOaY9vhlD-QjWVWNHUmLu48UKTb-QN9vXqrQxBgA,6907
|
518
|
-
sglang/srt/mem_cache/base_prefix_cache.py,sha256=NY62Zo0A0tLJ7ObRLOQqQcXCxoJUDZsK8f5U4dNQjKc,973
|
519
|
-
sglang/srt/mem_cache/chunk_cache.py,sha256=Lyv3eUEaYnCJCLoZQhCx5WfiiUCrrS4xti3e5VROl1A,1894
|
520
|
-
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
521
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=BJR-R2u5YyYIhGIxTY-3rf8Vx60XjCRU8Yhmkn2fzzM,16597
|
522
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=M1rKyPZ0TBLenO1nQgsjAwheBfMzcR3-B4hPNAEgCEQ,36358
|
523
|
-
sglang/srt/mem_cache/paged_allocator.py,sha256=BrJS0vN1k-vTSgb_M8u_1KoZFRgzgR1WRyImCTq3T0U,9770
|
524
|
-
sglang/srt/mem_cache/radix_cache.py,sha256=Lm-pco6CJ4orb9IfDpbHm5MnyK8Ya0OF1x9p88dv548,14906
|
525
|
-
sglang/srt/metrics/collector.py,sha256=o9s4j-QC6JK_S352QVkAUkz35my57gFPWyhh3WUIfiY,19569
|
526
|
-
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
527
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=toZ6OvNcxWQMoPcpifWgeoeJP-fGdwySVzdLkec8Oso,26310
|
528
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=b7XH72qIpslgEpy7hyMqCXtC_fWNm_yuqVtQRk8hWPw,27731
|
529
|
-
sglang/srt/model_executor/model_runner.py,sha256=J0B6nSs8oiuizHM653c0SY5PJ9BbqUmne8igPs1bUdg,49200
|
530
|
-
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
531
|
-
sglang/srt/model_loader/loader.py,sha256=-TISKGKpehU86vVyGm0xo2GALVVzQSUibi3jEisTBiw,55494
|
532
|
-
sglang/srt/model_loader/utils.py,sha256=0NaMR67fESFopaklmsleiL27XH1QUrjZW246MUu1EJ0,1369
|
533
|
-
sglang/srt/model_loader/weight_utils.py,sha256=yKnau-wH9muczoCpDTCVIqXFqz-QJmEEySplX3bMJWk,32153
|
534
|
-
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
535
|
-
sglang/srt/models/bert.py,sha256=kHlErDgNX_mIhfWWCnAcH_ncvYg22Y61gI34gW8GuUY,12738
|
536
|
-
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
537
|
-
sglang/srt/models/clip.py,sha256=58m-y5lkHIGY0ypYGtgD6gImQ7yZJutYGVl-ygqbNBI,19765
|
538
|
-
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
539
|
-
sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,15598
|
540
|
-
sglang/srt/models/deepseek.py,sha256=ZnN02HdgXCB23Vno5V9UMUoOxH5HC82vNTwsVulUJ-o,17206
|
541
|
-
sglang/srt/models/deepseek_janus_pro.py,sha256=OeeI7vZbE4HGpxa8CwT6-Lbfs7J7WMQ3oBNpVJQpv3w,70450
|
542
|
-
sglang/srt/models/deepseek_nextn.py,sha256=Yy5dItwimszQsAN7EjgND2cNQ9bypJ1TtFfhqcBQJnk,5673
|
543
|
-
sglang/srt/models/deepseek_v2.py,sha256=ueqi4m3S4rj8VL49MdXmxXrNHp2rAsYCfclcjLOafHg,75767
|
544
|
-
sglang/srt/models/deepseek_vl2.py,sha256=j8BdxZsMjm6lPdbDipEIKhVIVywCP1Vl1Kl46BZ5_0Y,13147
|
545
|
-
sglang/srt/models/exaone.py,sha256=rX7J0xFt9TSt6tMIhnYMkb5KDnqTJIV4BtjPLFwQ8_8,13425
|
546
|
-
sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
|
547
|
-
sglang/srt/models/gemma2.py,sha256=kqtwdo93GWKm2iBN29RoIRH2ggRm-K_80LM5btgfBLo,16395
|
548
|
-
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
549
|
-
sglang/srt/models/gemma3_causal.py,sha256=LfwHhF0nRD7OnmeHXXfQ7rofnFXjJI74gZiptak18RY,24924
|
550
|
-
sglang/srt/models/gemma3_mm.py,sha256=5rthHzaFNJb82IYUREwxQt4N4fDXW4lIxiptnKpVing,15246
|
551
|
-
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
552
|
-
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
553
|
-
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
554
|
-
sglang/srt/models/grok.py,sha256=vESZeGS4adI_JAerXIkCcTm15-CNiGeS7VHc36C6w1A,28033
|
555
|
-
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
556
|
-
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
557
|
-
sglang/srt/models/internvl.py,sha256=kEzkL5tAq3skvK5D7TqhiElSIXrA6cNOd8irYV4aKhA,24927
|
558
|
-
sglang/srt/models/kimi_vl.py,sha256=YoM6CmrF4ZS0SsXKiR-_SfylKhd87ciJjno6_x5LG4o,12874
|
559
|
-
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
560
|
-
sglang/srt/models/llama.py,sha256=-NC9EL9R8iJqaRrkMLewvTP3sgC_f07AHmGBVEdKmQ8,27149
|
561
|
-
sglang/srt/models/llama4.py,sha256=EZdosYTrzEX0oYnWqocTzB4n7U9_V8fIgJqGxrJn268,19385
|
562
|
-
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
563
|
-
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
564
|
-
sglang/srt/models/llama_eagle3.py,sha256=KCvUrWn17t7T28G60HwMyy99iB9AbdbPnS2el9n3r6o,6804
|
565
|
-
sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OWYfirZnA,3254
|
566
|
-
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
567
|
-
sglang/srt/models/llava.py,sha256=b9WcshvSqz1cqbuOq1tVTKH5J9D5PN5bBYrWzVKIQzo,37116
|
568
|
-
sglang/srt/models/llavavid.py,sha256=q0lHlRnoYHKJZsWnkIQdd6dYAQ26t7XsmrqA0zDGmZc,12829
|
569
|
-
sglang/srt/models/minicpm.py,sha256=m5HFsSJj0Po09LY9R6qj6K4gceqWDMOePz3NDGgMGT4,14691
|
570
|
-
sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
|
571
|
-
sglang/srt/models/minicpmo.py,sha256=BAiFR78L0j5WDZtOrUf6JgUe9DZs9huIsfQ_4RzUbdA,76319
|
572
|
-
sglang/srt/models/minicpmv.py,sha256=hSDWEcmutqOJv-xs0X_4TaNCDAWFUk71eRHLm9sPC0U,40564
|
573
|
-
sglang/srt/models/mistral.py,sha256=EYifJUUzN2Z2-iL37eJiNZF_DB0H4pa0mKlgYRIxM70,838
|
574
|
-
sglang/srt/models/mixtral.py,sha256=n-Pz7fyWE4m6Uh7sjzAYKNr5Wy4QUj5Yekl0qiCwQI8,17055
|
575
|
-
sglang/srt/models/mixtral_quant.py,sha256=-kQw9r8KcLdO8SNN9RKXzrGq9Q2Al9l9cWHi1VrZSRM,15260
|
576
|
-
sglang/srt/models/mllama.py,sha256=sOuP3Od3h9_uh_oxDN5rj4CzhZjg82PyElfBHuTxzUQ,39768
|
577
|
-
sglang/srt/models/mllama4.py,sha256=ejuhIVX0MDojdB5EPR-V-Qd_E9st8KYjnjyeArFbdFs,9084
|
578
|
-
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
579
|
-
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
580
|
-
sglang/srt/models/olmoe.py,sha256=TMzt-yB891bvA4X50xL0NjNnFYSx9imlA7N1EG8KNK0,15949
|
581
|
-
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
582
|
-
sglang/srt/models/pixtral.py,sha256=Iu7OTvM_nnApk1VjpUb1ucPBU2F1Kov5w6ddYn7gGqE,16983
|
583
|
-
sglang/srt/models/qwen.py,sha256=xYkVmMZS2uMqWhfndc8EYm0olpKFnggfuMp_6aobVi4,10758
|
584
|
-
sglang/srt/models/qwen2.py,sha256=ab912Yyk0aXOzI-wrxqN-sNF3bTVkNxB8P2uNcOCv9U,16394
|
585
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=LQee0Yuz6XzKiIFZQBUgRuDN2aX_CqvoxHx7w5a35ww,22603
|
586
|
-
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
587
|
-
sglang/srt/models/qwen2_eagle.py,sha256=Iz0HWL2FgSD3FqoFhfYmbIZeEYkPTJ96lYbkncmHJX4,4644
|
588
|
-
sglang/srt/models/qwen2_moe.py,sha256=iG0d2WwUosOFR9w2YGM9CfvZ1NG-rhse3OUTwSs8a6Q,18567
|
589
|
-
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
590
|
-
sglang/srt/models/qwen2_vl.py,sha256=X18_Smisiz6zQHUK4h7-ho8poRKWjUZisjB5LuUwYGk,20946
|
591
|
-
sglang/srt/models/qwen3.py,sha256=reaowGkotYAGHS5zTCWrvnyxtu92QKus19n-2amtMa4,12358
|
592
|
-
sglang/srt/models/qwen3_moe.py,sha256=A9Z3OhJqld1sJUDsHymgGxib4lMCMTKxF8iIzHDGdNo,15877
|
593
|
-
sglang/srt/models/registry.py,sha256=inKh9iwOp3LFYm3nqujg-OtABClOP-ifc1stA9cZegA,3434
|
594
|
-
sglang/srt/models/roberta.py,sha256=77H_-9jtjqpHlpQhBuZXs7RUG-dSjauDkpHhFe61DpE,6320
|
595
|
-
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
596
|
-
sglang/srt/models/torch_native_llama.py,sha256=oTxxof5Wx2b2egIwWx56LeHjtPGQleQ2zM5jXHMiuOU,19293
|
597
|
-
sglang/srt/models/xiaomi_mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
598
|
-
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
599
|
-
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
600
|
-
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
601
|
-
sglang/srt/openai_api/adapter.py,sha256=rTVMbR6jbY-lbMZL_VvWF-3E6FQrD2nb0HMg2OrBP88,77748
|
602
|
-
sglang/srt/openai_api/protocol.py,sha256=CsMwbu09RzmdZ5d6nrZ5di-5_kN1g8452kKBlX9sF6c,14353
|
603
|
-
sglang/srt/platforms/interface.py,sha256=hym3iooBB4C8if5hDZezgVN6h4NIOu7sg2ZUBIV6XmM,11246
|
604
|
-
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
605
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=VjOQpiXsY2vlTPtSb0T4piXIEtE54QefDpTVSDJ7bXE,11988
|
606
|
-
sglang/srt/sampling/sampling_params.py,sha256=tfUwWgxu6JWXsOClX_MFGTfetgRE63CQZsIpOhnWcoE,6013
|
607
|
-
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
608
|
-
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
609
|
-
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
610
|
-
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
611
|
-
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
612
|
-
sglang/srt/speculative/build_eagle_tree.py,sha256=lt4sXUehPi26MT2-2Z0VivtF6AP7kirSaEO_u-YJ4J4,11670
|
613
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=zQl6o6_T08UWIzkZbMghwVy_O2pLOyAYreM9VmyHRmY,9298
|
614
|
-
sglang/srt/speculative/eagle_utils.py,sha256=DKYmQrO1Mg4i_8e-7YpbVtDifMWxMkAG3rATRh9gQOQ,28694
|
615
|
-
sglang/srt/speculative/eagle_worker.py,sha256=M3vSOd2MHzECAcWogFuGjdYt-AGuHFqfODQDl_Bo6qE,27012
|
616
|
-
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
617
|
-
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
618
|
-
sglang/test/few_shot_gsm8k.py,sha256=qnEejCyPHGEMBEiNc7T4-t9lvoo2DNN72RXw-ei_TnY,4300
|
619
|
-
sglang/test/few_shot_gsm8k_engine.py,sha256=Yf1Dg0Tk-tY4v1oj_UTxJ7950CWn6kRMbQKDjT2Orgo,3902
|
620
|
-
sglang/test/run_eval.py,sha256=K4Z3OdMPvLeuGJhWWTBD0F-MOUFeBYLvsPnDQ44bd18,4036
|
621
|
-
sglang/test/runners.py,sha256=ryQXb7Jpg_ewqLSF9ZSy7BAwcB1gGeTBlw9MeknzTxE,30699
|
622
|
-
sglang/test/send_one.py,sha256=zIgnesgLDI3hcoZbYv4lpmizN44ZRmhShI2FbQauLrs,5003
|
623
|
-
sglang/test/simple_eval_common.py,sha256=OW4Z7O33QqDySRFuHIC4Ouidfup4eaOEuR9i7xJzkDY,12379
|
624
|
-
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
625
|
-
sglang/test/simple_eval_humaneval.py,sha256=s8YuKIBkNUEOBP4XKsTMRdXGv5aRhl0oJyl-89lGk1w,5687
|
626
|
-
sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWUpk,2550
|
627
|
-
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
628
|
-
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
629
|
-
sglang/test/test_activation.py,sha256=GeTIJHxlLQfW3kM-X1FGa8Sa3dSGKHEXl5wEy-hfGis,1489
|
630
|
-
sglang/test/test_block_fp8.py,sha256=bsV6Y_tCUF2ROEmuPDegNmHzGF-T4AgOvH7eYmAmKtA,21604
|
631
|
-
sglang/test/test_block_fp8_ep.py,sha256=N1rvqbPErBaFFpeAw8TLYXGNZOoG7cfIBP2p5XbSyMo,10806
|
632
|
-
sglang/test/test_custom_ops.py,sha256=2bSo9P5_rJZYFq8Y8IKRimDfFyZZGJluhL7Ngny0Pf4,5571
|
633
|
-
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
634
|
-
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
635
|
-
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
636
|
-
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
637
|
-
sglang/test/test_utils.py,sha256=XijnLXyC7t1Kfg_yz3Y426DgQx8PYsE8iOesdHLAPY8,35032
|
638
|
-
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
639
|
-
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
640
|
-
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
641
|
-
sglang/test/attention/test_prefix_chunk_info.py,sha256=er0i3KGHMkw-4UZB1GCFd4oYwRcXfU5wpO1ORqpNGGA,7626
|
642
|
-
sglang-0.4.6.post4.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
643
|
-
sglang-0.4.6.post4.dist-info/METADATA,sha256=LYS-QShEa42mO05m4fh0JjTDKD9a4rKtxYaB2vNK_jk,26006
|
644
|
-
sglang-0.4.6.post4.dist-info/WHEEL,sha256=DnLRTWE75wApRYVsjgc6wsVswC54sMSJhAEd4xhDpBk,91
|
645
|
-
sglang-0.4.6.post4.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
646
|
-
sglang-0.4.6.post4.dist-info/RECORD,,
|