sglang 0.4.6.post5__py3-none-any.whl → 0.4.7.post1__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/__init__.py +2 -0
- sglang/api.py +7 -0
- sglang/bench_offline_throughput.py +10 -4
- sglang/bench_one_batch_server.py +67 -11
- sglang/bench_serving.py +86 -75
- sglang/lang/backend/runtime_endpoint.py +24 -1
- sglang/lang/interpreter.py +40 -1
- sglang/lang/ir.py +27 -0
- sglang/math_utils.py +8 -0
- 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 +33 -1
- 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 +52 -8
- sglang/srt/custom_op.py +38 -3
- sglang/srt/debug_utils.py +74 -0
- sglang/srt/disaggregation/base/__init__.py +1 -1
- sglang/srt/disaggregation/base/conn.py +25 -11
- sglang/srt/disaggregation/common/__init__.py +5 -0
- sglang/srt/disaggregation/common/conn.py +407 -0
- sglang/srt/disaggregation/common/utils.py +42 -0
- sglang/srt/disaggregation/decode.py +261 -52
- sglang/srt/disaggregation/fake/__init__.py +1 -1
- sglang/srt/disaggregation/fake/conn.py +16 -9
- sglang/srt/disaggregation/kv_events.py +60 -5
- sglang/srt/disaggregation/launch_lb.py +140 -0
- sglang/srt/disaggregation/mini_lb.py +29 -48
- sglang/srt/disaggregation/mooncake/__init__.py +1 -1
- sglang/srt/disaggregation/mooncake/conn.py +446 -149
- sglang/srt/disaggregation/mooncake/transfer_engine.py +32 -16
- sglang/srt/disaggregation/nixl/__init__.py +6 -1
- sglang/srt/disaggregation/nixl/conn.py +134 -437
- sglang/srt/disaggregation/prefill.py +130 -43
- sglang/srt/disaggregation/utils.py +127 -86
- sglang/srt/distributed/device_communicators/pymscclpp.py +315 -0
- sglang/srt/distributed/parallel_state.py +52 -5
- sglang/srt/entrypoints/EngineBase.py +6 -0
- sglang/srt/entrypoints/engine.py +116 -5
- sglang/srt/entrypoints/http_server.py +28 -4
- sglang/srt/eplb_simulator/__init__.py +1 -0
- sglang/srt/eplb_simulator/reader.py +51 -0
- sglang/srt/function_call/base_format_detector.py +138 -86
- sglang/srt/function_call/deepseekv3_detector.py +54 -6
- sglang/srt/function_call/ebnf_composer.py +33 -19
- sglang/srt/function_call/function_call_parser.py +27 -0
- sglang/srt/function_call/llama32_detector.py +33 -14
- sglang/srt/function_call/mistral_detector.py +73 -26
- sglang/srt/function_call/pythonic_detector.py +86 -20
- sglang/srt/function_call/qwen25_detector.py +64 -10
- sglang/srt/function_call/utils.py +17 -0
- sglang/srt/hf_transformers_utils.py +4 -0
- sglang/srt/layers/activation.py +19 -0
- sglang/srt/layers/attention/aiter_backend.py +503 -125
- sglang/srt/layers/attention/base_attn_backend.py +4 -0
- sglang/srt/layers/attention/cutlass_mla_backend.py +40 -34
- sglang/srt/layers/attention/flashattention_backend.py +137 -63
- sglang/srt/layers/attention/flashinfer_backend.py +46 -3
- sglang/srt/layers/attention/flashinfer_mla_backend.py +59 -25
- sglang/srt/layers/attention/flashmla_backend.py +2 -10
- 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 +304 -65
- sglang/srt/layers/attention/triton_ops/decode_attention.py +2 -7
- sglang/srt/layers/attention/triton_ops/extend_attention.py +12 -4
- sglang/srt/layers/attention/vision.py +51 -24
- sglang/srt/layers/communicator.py +281 -197
- sglang/srt/layers/dp_attention.py +6 -5
- sglang/srt/layers/layernorm.py +30 -19
- sglang/srt/layers/linear.py +0 -4
- sglang/srt/layers/logits_processor.py +0 -12
- sglang/srt/layers/moe/cutlass_moe.py +170 -7
- sglang/srt/layers/moe/cutlass_moe_params.py +169 -0
- sglang/srt/layers/moe/ep_moe/kernels.py +33 -11
- sglang/srt/layers/moe/ep_moe/layer.py +136 -72
- sglang/srt/layers/moe/ep_moe/token_dispatcher.py +24 -45
- 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 +221 -29
- sglang/srt/layers/moe/fused_moe_triton/layer.py +34 -4
- sglang/srt/layers/moe/topk.py +60 -26
- sglang/srt/layers/multimodal.py +3 -3
- sglang/srt/layers/pooler.py +56 -0
- sglang/srt/layers/quantization/__init__.py +3 -2
- 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_wrapper/__init__.py +1 -0
- sglang/srt/layers/quantization/{deep_gemm.py → deep_gemm_wrapper/compile_utils.py} +69 -127
- sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py +32 -0
- sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py +110 -0
- sglang/srt/layers/quantization/fp8.py +28 -23
- sglang/srt/layers/quantization/fp8_kernel.py +156 -75
- sglang/srt/layers/quantization/fp8_utils.py +250 -69
- sglang/srt/layers/quantization/modelopt_quant.py +334 -7
- sglang/srt/layers/quantization/moe_wna16.py +3 -0
- sglang/srt/layers/quantization/w8a8_fp8.py +3 -0
- sglang/srt/layers/quantization/w8a8_int8.py +3 -0
- sglang/srt/layers/radix_attention.py +2 -3
- 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 +98 -39
- sglang/srt/lora/mem_pool.py +28 -21
- sglang/srt/lora/utils.py +17 -13
- sglang/srt/managers/cache_controller.py +2 -1
- 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/{deepseek_eplb.py → eplb_algorithms/deepseek_vec.py} +5 -7
- sglang/srt/managers/eplb_manager.py +55 -14
- sglang/srt/managers/expert_distribution.py +220 -46
- sglang/srt/managers/expert_location.py +110 -56
- sglang/srt/managers/expert_location_dispatch.py +23 -6
- sglang/srt/managers/io_struct.py +43 -8
- sglang/srt/managers/mm_utils.py +88 -38
- sglang/srt/managers/multimodal_processors/base_processor.py +190 -18
- sglang/srt/managers/multimodal_processors/gemma3.py +4 -31
- sglang/srt/managers/multimodal_processors/internvl.py +4 -0
- sglang/srt/managers/multimodal_processors/kimi_vl.py +15 -34
- sglang/srt/managers/multimodal_processors/minicpm.py +2 -1
- sglang/srt/managers/multimodal_processors/phi4mm.py +87 -0
- sglang/srt/managers/multimodal_processors/qwen_vl.py +22 -64
- sglang/srt/managers/multimodal_processors/vila.py +85 -0
- sglang/srt/managers/schedule_batch.py +173 -38
- sglang/srt/managers/scheduler.py +376 -127
- sglang/srt/managers/tokenizer_manager.py +163 -19
- sglang/srt/managers/utils.py +0 -4
- sglang/srt/mem_cache/chunk_cache.py +1 -0
- sglang/srt/mem_cache/hiradix_cache.py +4 -2
- sglang/srt/mem_cache/memory_pool.py +111 -407
- sglang/srt/mem_cache/memory_pool_host.py +380 -0
- sglang/srt/mem_cache/radix_cache.py +36 -12
- sglang/srt/metrics/collector.py +9 -0
- sglang/srt/model_executor/cuda_graph_runner.py +191 -113
- sglang/srt/model_executor/expert_location_updater.py +157 -22
- sglang/srt/model_executor/forward_batch_info.py +52 -22
- sglang/srt/model_executor/model_runner.py +102 -62
- sglang/srt/model_loader/loader.py +8 -1
- sglang/srt/model_loader/utils.py +67 -1
- sglang/srt/models/bert.py +113 -13
- sglang/srt/models/deepseek_nextn.py +1 -1
- sglang/srt/models/deepseek_v2.py +623 -290
- sglang/srt/models/gemma3_causal.py +7 -0
- sglang/srt/models/gemma3_mm.py +19 -14
- sglang/srt/models/idefics2.py +342 -0
- sglang/srt/models/internvl.py +46 -102
- sglang/srt/models/kimi_vl.py +4 -4
- sglang/srt/models/llama.py +1 -1
- sglang/srt/models/minicpmo.py +2 -5
- sglang/srt/models/minicpmv.py +3 -295
- sglang/srt/models/phi4mm.py +512 -0
- sglang/srt/models/qwen2.py +38 -9
- sglang/srt/models/qwen2_5_vl.py +3 -9
- sglang/srt/models/qwen2_eagle.py +4 -1
- sglang/srt/models/qwen2_moe.py +58 -191
- sglang/srt/models/qwen2_vl.py +3 -9
- sglang/srt/models/qwen3.py +41 -10
- sglang/srt/models/qwen3_moe.py +230 -191
- sglang/srt/models/registry.py +9 -1
- sglang/srt/models/roberta.py +117 -9
- sglang/srt/models/transformers.py +291 -0
- sglang/srt/models/vila.py +305 -0
- sglang/srt/openai_api/adapter.py +248 -28
- sglang/srt/openai_api/protocol.py +68 -3
- sglang/srt/openai_api/utils.py +172 -0
- sglang/srt/operations.py +37 -2
- sglang/srt/operations_strategy.py +200 -24
- sglang/srt/sampling/sampling_batch_info.py +37 -1
- sglang/srt/sampling/sampling_params.py +4 -1
- sglang/srt/server_args.py +381 -209
- sglang/srt/speculative/build_eagle_tree.py +9 -9
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +12 -14
- sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py +256 -0
- sglang/srt/speculative/eagle_utils.py +440 -200
- sglang/srt/speculative/eagle_worker.py +234 -63
- sglang/srt/two_batch_overlap.py +637 -0
- sglang/srt/utils.py +187 -7
- sglang/test/attention/test_prefix_chunk_info.py +2 -0
- sglang/test/runners.py +54 -10
- sglang/test/send_one.py +4 -0
- sglang/test/test_block_fp8.py +1 -0
- sglang/test/test_block_fp8_deep_gemm_blackwell.py +252 -0
- sglang/test/test_block_fp8_ep.py +1 -0
- sglang/test/test_cutlass_moe.py +3 -3
- sglang/test/test_fp4_moe.py +248 -0
- sglang/test/test_utils.py +82 -7
- sglang/utils.py +9 -0
- sglang/version.py +1 -1
- {sglang-0.4.6.post5.dist-info → sglang-0.4.7.post1.dist-info}/METADATA +17 -14
- {sglang-0.4.6.post5.dist-info → sglang-0.4.7.post1.dist-info}/RECORD +359 -321
- {sglang-0.4.6.post5.dist-info → sglang-0.4.7.post1.dist-info}/WHEEL +1 -1
- /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-0.4.6.post5.dist-info → sglang-0.4.7.post1.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.6.post5.dist-info → sglang-0.4.7.post1.dist-info}/top_level.txt +0 -0
@@ -1,45 +1,49 @@
|
|
1
|
-
sglang/__init__.py,sha256=
|
2
|
-
sglang/api.py,sha256=
|
3
|
-
sglang/bench_offline_throughput.py,sha256=
|
1
|
+
sglang/__init__.py,sha256=x1v8748WXS2BAptWAd5fR3YBEkngC7e_P_rkCNuNCGg,1702
|
2
|
+
sglang/api.py,sha256=rcp3GeoyZhmJ0GDLPRkuZNcxd0TBJy_wfUDpcmQoqW8,7210
|
3
|
+
sglang/bench_offline_throughput.py,sha256=TwgXZYmwPaHVsdPtNU9LO0p1tr5OOKLy9wYgrfGAlFU,14056
|
4
4
|
sglang/bench_one_batch.py,sha256=fCxRRk14uQqTxpriBkrUkvrOUjNT7TZgDeGGWJQzhgw,19328
|
5
|
-
sglang/bench_one_batch_server.py,sha256=
|
6
|
-
sglang/bench_serving.py,sha256=
|
5
|
+
sglang/bench_one_batch_server.py,sha256=4Jbs8UI-Sbt3TL3SJBC3fySZPe4apz2glKWOvvaYsQQ,13486
|
6
|
+
sglang/bench_serving.py,sha256=EzZn91DuScAEhUMQv-LPWm3UoGjzj8OEzHMzVwoEA34,65672
|
7
7
|
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
8
8
|
sglang/compile_deep_gemm.py,sha256=H118s76CKdpZr-cDeFfBCePe7--c_teEBNVIzchYVSo,6243
|
9
9
|
sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
|
10
10
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
11
|
-
sglang/
|
12
|
-
sglang/
|
11
|
+
sglang/math_utils.py,sha256=QYtbaIA76P33ojcOrL32VR6yXWv-Od_3WCZNO4kQ-YQ,177
|
12
|
+
sglang/profiler.py,sha256=tEHzHerXC-ymk4OrkoUcMbgcGHmb8VESthsNSP2Yx9w,4417
|
13
|
+
sglang/utils.py,sha256=VH6zrnkjzcR3DE__WfVph6wswJ4JuzoQD47VmbZ38eI,16435
|
14
|
+
sglang/version.py,sha256=rkzrlJTNQdK78CIF17Jk3y_9tOj5bACvLDEnSq4qJRw,28
|
13
15
|
sglang/eval/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
14
16
|
sglang/eval/loogle_eval.py,sha256=pRPVA4fxGmT3_oXvXnlNE-UlPrcQGLBJF-OSE9YWJXM,4336
|
15
17
|
sglang/lang/chat_template.py,sha256=HKlx7snSWFED8GKF5ex79sQrPWFw5TSXQM0_LsiD9Bc,20552
|
16
18
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
17
19
|
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
18
|
-
sglang/lang/interpreter.py,sha256=
|
19
|
-
sglang/lang/ir.py,sha256=
|
20
|
+
sglang/lang/interpreter.py,sha256=JneG-Yw-XyOTBZCIoxTiQluQjAlSz1YswnV0l6pqVPo,34811
|
21
|
+
sglang/lang/ir.py,sha256=FnRJ-lndAsR4GR0ONJRPDtlYx8FvL9RIk44vSA16RBk,19656
|
20
22
|
sglang/lang/tracer.py,sha256=ljBo9VZ0zVaGwzNk32qw21acyo60N0UjIjqBbT5a1WI,8175
|
21
23
|
sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
22
24
|
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
23
25
|
sglang/lang/backend/base_backend.py,sha256=tEutGCU5tni1xGlrIjAVvA9aflJBt2duKrIDzqabJWc,1975
|
24
26
|
sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThcY,2450
|
25
27
|
sglang/lang/backend/openai.py,sha256=YFs7pCDK6_DoYmjTa-vgDVdaeE4PYr7E-sIC1q7vAns,16422
|
26
|
-
sglang/lang/backend/runtime_endpoint.py,sha256=
|
28
|
+
sglang/lang/backend/runtime_endpoint.py,sha256=oxLCLXCa26VfKyPV-wbRjLrQvqTG8NzoaVgwczzyIYc,17481
|
27
29
|
sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZpI,4827
|
28
|
-
sglang/srt/_custom_ops.py,sha256=
|
30
|
+
sglang/srt/_custom_ops.py,sha256=Y56OZL-6cUBLVmCpWSSjmpsisRYbSE9H--Oq8NjzbPM,4437
|
29
31
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
30
32
|
sglang/srt/code_completion_parser.py,sha256=vafJqdTTreD9kvCsoMuxP_fFmoue7pOA1ibI9KXg4mE,5405
|
31
|
-
sglang/srt/conversation.py,sha256=
|
32
|
-
sglang/srt/custom_op.py,sha256=
|
33
|
-
sglang/srt/
|
33
|
+
sglang/srt/conversation.py,sha256=Ep72tO6lJ7vpyhCmzp5AGmrjDwc2VkegLs2gIklGm4g,36628
|
34
|
+
sglang/srt/custom_op.py,sha256=lIwo6blTAaPUqXnxy1xsmUJ0qCdp9poPKbZ4mRJAaN4,2734
|
35
|
+
sglang/srt/debug_utils.py,sha256=slaFOY4BYDBFatkfu8FZlzai-u4LFS-5GUzdr-t50zE,2241
|
36
|
+
sglang/srt/hf_transformers_utils.py,sha256=S1ZF4aFKTocenXvj9ti6M-buiCBus4FrP1AdwFz_Wbw,11943
|
34
37
|
sglang/srt/mm_utils.py,sha256=7o4w1W0VAWgEquVIz7qw7-IxYbZY2g3MrXw9php90oY,12621
|
35
38
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
36
|
-
sglang/srt/operations.py,sha256=
|
37
|
-
sglang/srt/operations_strategy.py,sha256=
|
39
|
+
sglang/srt/operations.py,sha256=ddQ8KO63L73OciaR8MZ9h2h83gKVY4-WuWgeEGowPJA,5346
|
40
|
+
sglang/srt/operations_strategy.py,sha256=6DDLEdmkLrFDTXWZoFO0q9MZjEThvfyvoO-LbQsNpPQ,7023
|
38
41
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
39
42
|
sglang/srt/reasoning_parser.py,sha256=lZN5b1TJp3EK2GzxcICQhp0tRQjQw3ROOrjRgQe6Bsc,6341
|
40
|
-
sglang/srt/server_args.py,sha256=
|
43
|
+
sglang/srt/server_args.py,sha256=nz73pQa4Z6mI-2elebYMV0ajq3QLH1dQ3OBslp-G7wU,71676
|
41
44
|
sglang/srt/torch_memory_saver_adapter.py,sha256=HYlgYJ2sgmjs2RSjU2KbCaXijRg3mTDZ0ZcCB5Bt6Ps,2211
|
42
|
-
sglang/srt/
|
45
|
+
sglang/srt/two_batch_overlap.py,sha256=Q6tobqItnlK5ad9mqqMMx0HJ-PAzW4DgBtgSQ7Ax6sM,21848
|
46
|
+
sglang/srt/utils.py,sha256=Zl-xEOFgPyr91A9-q-0Y1PUobAmKvKURgSDR3EBGk4U,72516
|
43
47
|
sglang/srt/warmup.py,sha256=FmJiYfjRr3X_eAe7ojQaPoN17LvHpjDmRWRnO-k86AQ,1469
|
44
48
|
sglang/srt/configs/__init__.py,sha256=8EcVRP95epZ49DxBa6LgKWt7eO3Qe7Hrr3V1c6HkMnY,553
|
45
49
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
@@ -47,12 +51,12 @@ sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11
|
|
47
51
|
sglang/srt/configs/deepseekvl2.py,sha256=X8Q2gm7og_Ylx6tbFXetusfIJIXjWY_YH_p90C67BTI,23397
|
48
52
|
sglang/srt/configs/device_config.py,sha256=kdwFrk5myAURxdp4rSr8ANpBpSJfuBDoT-kuCyuscRs,442
|
49
53
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
50
|
-
sglang/srt/configs/internvl.py,sha256=
|
54
|
+
sglang/srt/configs/internvl.py,sha256=NseEdxsLPJNpj5iyDueYw836jZq7-swozC3hAkFnmtI,27401
|
51
55
|
sglang/srt/configs/janus_pro.py,sha256=Rrb7kQsNaUP-TiZrjNk8Lr1momFrql8ScEunnrH0_xM,19086
|
52
56
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
53
57
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
54
58
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
55
|
-
sglang/srt/configs/model_config.py,sha256=
|
59
|
+
sglang/srt/configs/model_config.py,sha256=mXERUkexcWnZxrCzpxaMo7FhYm-CNhwttDIVhw-ZysY,25206
|
56
60
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
57
61
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
58
62
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -62,276 +66,293 @@ sglang/srt/connector/utils.py,sha256=isTvxauz1_8no5MW6p8Bwj2H9mQkweaRO_RSwAPA7R8
|
|
62
66
|
sglang/srt/connector/serde/__init__.py,sha256=MvBJ7FBJtnou-AD-EdsCdAIDCcA8kWvUNuRViILVJ-0,718
|
63
67
|
sglang/srt/connector/serde/safe_serde.py,sha256=Iv_mFsDvk-cXuw0WTykBZ2yGxW0jb82DwVqC7r3RmAU,750
|
64
68
|
sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOUIhF0ZA,1004
|
65
|
-
sglang/srt/constrained/base_grammar_backend.py,sha256=
|
66
|
-
sglang/srt/constrained/llguidance_backend.py,sha256=
|
67
|
-
sglang/srt/constrained/outlines_backend.py,sha256=
|
69
|
+
sglang/srt/constrained/base_grammar_backend.py,sha256=6tYI1zoFjKU2sjn5nOyLxUJC5ZbyfoyiYkHLArmhSaI,6840
|
70
|
+
sglang/srt/constrained/llguidance_backend.py,sha256=Au8G8x4EB39w7k9-GFLP2hOPETyeAPw53RRZYdLimpA,6191
|
71
|
+
sglang/srt/constrained/outlines_backend.py,sha256=4Er45scnqHuJQ14kggsVX3RoHlaUD9t0ALIoWDQEmFg,6913
|
68
72
|
sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
|
69
73
|
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
70
|
-
sglang/srt/constrained/xgrammar_backend.py,sha256=
|
74
|
+
sglang/srt/constrained/xgrammar_backend.py,sha256=u9Ao-XX22UzALkATEAR_-0EoyBTxMTJV590qd9LAUHM,7906
|
71
75
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
72
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
76
|
+
sglang/srt/disaggregation/decode.py,sha256=vkxzLt843pcUe9gQI2M--25fyzCKpi0iGrLa7QPKFhA,33128
|
73
77
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=cUfd3-5lRHqWpwkrj4xdGMV2Hus08hdQbobTLNoCXlo,5569
|
74
|
-
sglang/srt/disaggregation/kv_events.py,sha256=
|
75
|
-
sglang/srt/disaggregation/
|
76
|
-
sglang/srt/disaggregation/
|
77
|
-
sglang/srt/disaggregation/
|
78
|
-
sglang/srt/disaggregation/
|
79
|
-
sglang/srt/disaggregation/base/
|
80
|
-
sglang/srt/disaggregation/
|
81
|
-
sglang/srt/disaggregation/
|
82
|
-
sglang/srt/disaggregation/
|
83
|
-
sglang/srt/disaggregation/
|
84
|
-
sglang/srt/disaggregation/
|
85
|
-
sglang/srt/disaggregation/
|
86
|
-
sglang/srt/disaggregation/
|
78
|
+
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
79
|
+
sglang/srt/disaggregation/launch_lb.py,sha256=mcbAztN4gnHevw_T5R2_nWsymsDEY9vHkm7OJ1vr6cc,4211
|
80
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=WGEdKQ0jMyRtZ1gG6q8uPnP9ovXkWGQamWZ3YmS4ng4,13429
|
81
|
+
sglang/srt/disaggregation/prefill.py,sha256=xj_Q5NT0DP-5bxV0Hct6PnevAVbG0ZA5r3dTcT1ivRo,23102
|
82
|
+
sglang/srt/disaggregation/utils.py,sha256=ih7KiJxyZF9Ma7O09UpBqkm8OCgfOvlg4odtoCK4uy4,10312
|
83
|
+
sglang/srt/disaggregation/base/__init__.py,sha256=4VwUv0aWxwmVL1049XK82aLTNxmt0WY5RPy9li-wyVk,160
|
84
|
+
sglang/srt/disaggregation/base/conn.py,sha256=6KK_7HL7xixVSB8iap8jjJrIv3JgHDmynZ39Os3k5MU,2771
|
85
|
+
sglang/srt/disaggregation/common/__init__.py,sha256=7yl-EGLMVKRpBUaGF_7lwAsw2J_mqpRZV0238VGxD9o,126
|
86
|
+
sglang/srt/disaggregation/common/conn.py,sha256=CZR1lMCE_mpSkvjc6BBmSr1SbHY1uZuxjpanazD-YXc,16071
|
87
|
+
sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeKVPMWPcB5ywbE,1194
|
88
|
+
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
89
|
+
sglang/srt/disaggregation/fake/conn.py,sha256=oD1DArn1yDFZCu-X6p93uSLlAXEkt9lYxERICMznxGw,2286
|
90
|
+
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
91
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=udV5-9Bg1CzBXAQasCYxdcxHmwTCGss4CHmsn7Vb_Rs,47871
|
92
|
+
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=gOcjZPtksJDq4iiIs0_zREdOM8trqUcmOXkrj-wiCuU,3149
|
93
|
+
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
94
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=KzVPRH8MaOAiG9EdfDN31sE9U9Ibsj2McDlSRWzHiP0,18055
|
87
95
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
88
96
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
89
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
97
|
+
sglang/srt/distributed/parallel_state.py,sha256=l4vrGXIr9ykd0imtzKdMjnBrQPRvbrYg0jQ9trDkdzI,53527
|
90
98
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
91
99
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
92
100
|
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=qje-PQ3v8yaV-oYVLPws1mgIlXVsGKFCOvXHmSe8ZXg,19624
|
93
101
|
sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py,sha256=fLoptT_U0lVAqkhEg-ge53CdFSIKQpDRiqHYKwJVEZg,10974
|
94
102
|
sglang/srt/distributed/device_communicators/hpu_communicator.py,sha256=gPjEH1-izoby5uDrfUlzNf21luPT0Ow7pJjhCRKnHy8,1728
|
95
103
|
sglang/srt/distributed/device_communicators/npu_communicator.py,sha256=bRXN1Md_4SHQGzQYZa2GrHv2zbIU5vSpkueHiAZL1xQ,1345
|
104
|
+
sglang/srt/distributed/device_communicators/pymscclpp.py,sha256=8Pgehd02v-BpHixTTB4OB9ZlxA7fyXiPF4Xp9F_heyU,10890
|
96
105
|
sglang/srt/distributed/device_communicators/pynccl.py,sha256=obXyCaZznZHSt486XCnEOBNG3Cen7ysuuMuGRlTTl-8,10095
|
97
106
|
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6EMz-oPS9J16WHo2Q_SRL1DtlJKK63Hfg,15349
|
98
107
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=d8mykYmXM1lfbPm8GNtqCF0Un_pdXYjbNmsgoVFyyow,20874
|
99
108
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
100
|
-
sglang/srt/entrypoints/EngineBase.py,sha256=
|
101
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
102
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
109
|
+
sglang/srt/entrypoints/EngineBase.py,sha256=FCwqQMJE_8CCCMThAXUZaKafsHvh2BaQ31J-7_ormwA,2310
|
110
|
+
sglang/srt/entrypoints/engine.py,sha256=SkBxdo6UDcQBOHbfpcfGrXsv0To92j_3BsdkA3Z6y1Y,30316
|
111
|
+
sglang/srt/entrypoints/http_server.py,sha256=F-yBo8nKYhFqi-WYvrHOGLmWpghEUqsc__BzB7xjlcI,31965
|
103
112
|
sglang/srt/entrypoints/http_server_engine.py,sha256=0QJFmrKAVnBmFbObHrmvUDcxDAsvnv6H29cQq286CKc,4939
|
104
113
|
sglang/srt/entrypoints/verl_engine.py,sha256=RYizNetTHzcB8dErX1EW4NsyRNGkFPljYaAf7pVRPdM,7002
|
105
|
-
sglang/srt/
|
114
|
+
sglang/srt/eplb_simulator/__init__.py,sha256=HIZaXqsvsOCMMJ81dSs1afSGZ5G6OiOZEtHpltyzzjY,21
|
115
|
+
sglang/srt/eplb_simulator/reader.py,sha256=R9wV7PqaCjILSnfYk90hNY95iJeST08a55Uj2Qk4iE0,1832
|
116
|
+
sglang/srt/function_call/base_format_detector.py,sha256=Ol8VaVrilkBhnjUUmWlt6E0eazvFd5gFrzNx0_x0_iw,12755
|
106
117
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
107
|
-
sglang/srt/function_call/deepseekv3_detector.py,sha256=
|
108
|
-
sglang/srt/function_call/ebnf_composer.py,sha256=
|
109
|
-
sglang/srt/function_call/function_call_parser.py,sha256=
|
110
|
-
sglang/srt/function_call/llama32_detector.py,sha256=
|
111
|
-
sglang/srt/function_call/mistral_detector.py,sha256=
|
112
|
-
sglang/srt/function_call/pythonic_detector.py,sha256=
|
113
|
-
sglang/srt/function_call/qwen25_detector.py,sha256=
|
114
|
-
sglang/srt/function_call/utils.py,sha256=
|
115
|
-
sglang/srt/layers/activation.py,sha256=
|
116
|
-
sglang/srt/layers/communicator.py,sha256=
|
117
|
-
sglang/srt/layers/dp_attention.py,sha256=
|
118
|
+
sglang/srt/function_call/deepseekv3_detector.py,sha256=FO5wbBMj1l9culkmZeC-LKguyRuqHcQOyX7NCEgfzTQ,8962
|
119
|
+
sglang/srt/function_call/ebnf_composer.py,sha256=02oDBr_dhxqlpCFBLItodSPbul9xEHlet7O7KkWZEZo,10686
|
120
|
+
sglang/srt/function_call/function_call_parser.py,sha256=8YqFlyxFHkp0DlUxe0TabTdV-Qx5SbaoURZrc8SfNJ8,7674
|
121
|
+
sglang/srt/function_call/llama32_detector.py,sha256=_d_pdzhn6Ut0jsivurki797hPK3vcNYjmXUkJ5sPKbk,3611
|
122
|
+
sglang/srt/function_call/mistral_detector.py,sha256=D2udBa9K1J6DdSPyJCp6JpaqYnrOMwoHYCjbHMWHxCc,4454
|
123
|
+
sglang/srt/function_call/pythonic_detector.py,sha256=waFdfHJuNg9DanTRDNWgh-Ji8TQkebcldUDPj0Xm8kk,8723
|
124
|
+
sglang/srt/function_call/qwen25_detector.py,sha256=YYDXHBcW1EQpZd0xzL92E6NBLG5t6vqPYOmFRACMdcw,4874
|
125
|
+
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
126
|
+
sglang/srt/layers/activation.py,sha256=GNp9qww-EF6JCvTY5_FVWtqodr2j6m0lhP7vmksnBNo,6647
|
127
|
+
sglang/srt/layers/communicator.py,sha256=_H-ZkyDeu8Y1v4BkeiexHKsx2MK3qQCPFodoMqxN80U,18639
|
128
|
+
sglang/srt/layers/dp_attention.py,sha256=oQ8qMzcv3r-x0GW8_j_D-BaGIM5BhQ_ehi-TkqIE4O4,9274
|
118
129
|
sglang/srt/layers/elementwise.py,sha256=XCrR2i-9dP-H6jQo2zUuquwZrsl_wEQqj5Wxk6WUf7o,13987
|
119
|
-
sglang/srt/layers/layernorm.py,sha256=
|
120
|
-
sglang/srt/layers/linear.py,sha256=
|
121
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
122
|
-
sglang/srt/layers/multimodal.py,sha256=
|
130
|
+
sglang/srt/layers/layernorm.py,sha256=VW46eTmFLFo7KezfwMKvwXlC_NPUVMGb93K2WREgldY,6325
|
131
|
+
sglang/srt/layers/linear.py,sha256=xdAv5qJodLdapHi9ex3e0Qa_KHldcGwEiE-LpLRs1U8,51939
|
132
|
+
sglang/srt/layers/logits_processor.py,sha256=KGYC4rPTLCHRnV-yL2E3ACj-bxO0BVZcQ_ZEUl9UNgk,25207
|
133
|
+
sglang/srt/layers/multimodal.py,sha256=YVR69WW-2aGDcZHT8IVJ6F_LRM7wraZr8VjrPDXqDmA,2104
|
123
134
|
sglang/srt/layers/parameter.py,sha256=zqWyEzpWzP4NNTjq3G9khq6XofgpcmJqQLg6Vd4WyWE,15084
|
124
|
-
sglang/srt/layers/pooler.py,sha256=
|
125
|
-
sglang/srt/layers/radix_attention.py,sha256=
|
126
|
-
sglang/srt/layers/rotary_embedding.py,sha256=
|
127
|
-
sglang/srt/layers/sampler.py,sha256=
|
135
|
+
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
136
|
+
sglang/srt/layers/radix_attention.py,sha256=IlqRB4bk06FOH05_7zB8lik0xLpys7jFooLeCwdO0j8,3437
|
137
|
+
sglang/srt/layers/rotary_embedding.py,sha256=G70hvJbPV0Jeh80wuEUCNc2AKB-P9sJIscPHoRvoFT0,48011
|
138
|
+
sglang/srt/layers/sampler.py,sha256=h30VHnKyNVtTkRvOhQWIAFvCY1abx2fw1d5zeE8N57o,11169
|
128
139
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
129
|
-
sglang/srt/layers/utils.py,sha256=
|
140
|
+
sglang/srt/layers/utils.py,sha256=IWGg1Hb7c33Z3LHRPVJyUAzp3BnSid23ZWXAmJ_Jvp8,1204
|
130
141
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=GPKCQiR2yH5Z2XSE9g3vWObdegcwPnMHXv7qEZovLH4,22755
|
131
|
-
sglang/srt/layers/attention/aiter_backend.py,sha256=
|
132
|
-
sglang/srt/layers/attention/base_attn_backend.py,sha256=
|
133
|
-
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=
|
142
|
+
sglang/srt/layers/attention/aiter_backend.py,sha256=CXFcu-PwUjhhQj02AWQop3lUzsvAF3K5OsGjz0Qahqs,32797
|
143
|
+
sglang/srt/layers/attention/base_attn_backend.py,sha256=HCdOMceZQAmIzZTewwp1_EIRfb1URlQZ3uGUmDKWw-o,3445
|
144
|
+
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=cZzKjxN7pm0J75dDrKMNKSaMVbZZGncM9mXS9CwqWLI,9784
|
134
145
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
135
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
136
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
137
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
138
|
-
sglang/srt/layers/attention/flashmla_backend.py,sha256=
|
146
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=9U2_gxJZafBoSPUM34sVtYxESHBHCnyZVr6eUHEjJWU,92296
|
147
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=a2PsYEoNrmZ7aXG9FDcPebkaBgUQ5DOcf5AWtte7yi0,49567
|
148
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=I_94zj9BlbUPc9Do4E2WE75xUA05xB_QZWYOvWv6hvI,33957
|
149
|
+
sglang/srt/layers/attention/flashmla_backend.py,sha256=spXbr5Dtl9u4saiBcxAFbsDktbidexQIpvX6J2ZffZA,20615
|
150
|
+
sglang/srt/layers/attention/intel_amx_backend.py,sha256=hH9lxXs_o66_IVs58oPhRCOXGUrHbXSz82FKtHr9GO8,4092
|
139
151
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
140
|
-
sglang/srt/layers/attention/
|
141
|
-
sglang/srt/layers/attention/
|
152
|
+
sglang/srt/layers/attention/tbo_backend.py,sha256=5EuuVA3MEeooQ5jkvANYODZc92lVlTRuijo0ZELixDw,8092
|
153
|
+
sglang/srt/layers/attention/torch_native_backend.py,sha256=RsI4lYiQJAj-Xy0vKkzbyKOWHAVPOD9b0n0dEehwlos,9496
|
154
|
+
sglang/srt/layers/attention/triton_backend.py,sha256=Ao6hoiknuOKuXT6kGltMHbYEx1dCM00C3EzbwvyyPSk,36644
|
142
155
|
sglang/srt/layers/attention/utils.py,sha256=KiRSIHaGBhErUhPWCSD3Uiaqb0pSEF0NJFwTTQXoMks,2887
|
143
|
-
sglang/srt/layers/attention/vision.py,sha256
|
144
|
-
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=
|
156
|
+
sglang/srt/layers/attention/vision.py,sha256=-wGBZs9TSY8px-KidPQpEevZiQd577HJ-Wl5cTKQgWM,16291
|
157
|
+
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=eN0Lqpu5h27lMPuRnisX4jrU0WR061pCFSrh3vLlSD0,18936
|
145
158
|
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
146
|
-
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=
|
159
|
+
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=ImpCuxszoeVdr6wzaLR3OGW3-50P9EAEvsRCdUVIrxE,14261
|
147
160
|
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
148
161
|
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
149
162
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
150
|
-
sglang/srt/layers/moe/cutlass_moe.py,sha256
|
151
|
-
sglang/srt/layers/moe/
|
163
|
+
sglang/srt/layers/moe/cutlass_moe.py,sha256=--bNTA2BGbHeULb_XXDoRUyWWbE-doHo5K5k1T0N0WA,14323
|
164
|
+
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
165
|
+
sglang/srt/layers/moe/fused_moe_native.py,sha256=FIES6H7oS-XjwVsWSrAkQzTdnp7kq-Z5VoViqOHpmtg,4851
|
152
166
|
sglang/srt/layers/moe/router.py,sha256=5Aeqoix_AS4uymb665OJE904wVSBkQeFdZP4e7KKPvg,10530
|
153
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
167
|
+
sglang/srt/layers/moe/topk.py,sha256=7l3oouJSdVfwT0KyZce74EKk5y7otFjGhGmL8IQWIX4,15216
|
154
168
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
155
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256
|
156
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
157
|
-
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=
|
169
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=EhCYANB_y1_NpW-mYDMw0jYCzftlVNLcm4fqbB4xK7I,34975
|
170
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=sXwTcjWeC1Ka_UW3Jzu7tG4PXXIEZvKiOEEdzrqt190,45006
|
171
|
+
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=wPc0ewfBeoyYmgKMbp1YoT81OaJSme7AmftrXbxR7Jg,23523
|
158
172
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
|
159
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
160
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
161
|
-
"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
|
162
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JJN0hryyLr5Zv3dSS7C8cPFhAwTT6XxUVnBGMZvV6JA,2752
|
163
|
-
"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
|
164
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=dd4aQZ1afXaEGS3ZUH31Yc3maWhT4L61m22QTxjqBm8,4141
|
165
|
-
"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
|
166
|
-
"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
|
167
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ypxsH-62Mw2Td6I8k6K8A52D9ORsUtwcBThhz-h7f2I,4150
|
168
|
-
"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
|
169
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=yf33YmWlVSjjyg0Q4OMAWvc9gjRxvttMrQBUEOfPl4I,4153
|
170
|
-
"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
|
171
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=C65Q2Mv1LxFQ_qDnv11IZ9nwl7sGZo72nWDflMttu4g,4147
|
172
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
173
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
174
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
175
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
176
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
177
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
178
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
179
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
180
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
181
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
182
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
183
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
184
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
185
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
186
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
187
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
188
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
189
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
190
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=
|
191
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=
|
192
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=
|
193
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=
|
194
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=
|
195
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
196
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
197
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
198
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
199
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
200
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
201
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
202
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
203
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
204
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
205
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
206
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
207
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
208
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
209
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
210
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
211
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
212
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
213
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
214
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
215
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
216
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
217
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
218
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
219
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
220
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
221
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
222
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
223
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
224
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
225
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
226
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
227
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
228
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
229
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
230
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
231
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
232
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
233
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
234
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
235
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
236
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
237
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
238
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
239
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
240
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
241
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
242
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
243
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
244
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
245
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
246
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
247
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
248
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
249
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
250
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
251
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
252
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
253
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
254
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
255
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
256
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
257
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
258
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
259
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
260
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
261
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
262
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
263
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
264
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
265
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
266
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
267
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
268
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
269
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
270
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
271
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
272
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
273
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
274
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
275
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
276
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
277
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
278
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
279
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
280
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
281
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
282
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
283
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
284
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
285
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
286
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
287
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=
|
288
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
289
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
290
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
291
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
292
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
293
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
294
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
295
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
296
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
297
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
298
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
299
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
300
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
301
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
302
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
303
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
304
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
305
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
306
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
307
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
308
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
309
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
310
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
311
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
312
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
313
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
314
|
-
sglang/srt/layers/
|
173
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=sIv67ShhS-6QeZxncNN_R_sH_SbfL2uW7yUAs8xolN0,62952
|
174
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=ptJveWp0alXFiwvL6FyXOH5Us4YPbKj4bg5om8JuEmE,27073
|
175
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
176
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JJN0hryyLr5Zv3dSS7C8cPFhAwTT6XxUVnBGMZvV6JA,2752
|
177
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ouRyZ5PEMPP2njPftCNhs-1g1y6wueWLmhI7G1SjV1k,4131
|
178
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=dd4aQZ1afXaEGS3ZUH31Yc3maWhT4L61m22QTxjqBm8,4141
|
179
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=8GLZzOVJNpfOXXMQaMtvcpQICzPG3jDNARvH4PxHX-s,4134
|
180
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=s-7qBDx_J3mFu09Nk14ZVseGeX5GPNRStQjohRCYt6k,4147
|
181
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ypxsH-62Mw2Td6I8k6K8A52D9ORsUtwcBThhz-h7f2I,4150
|
182
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=2Z27aKdaA4VxqtICk-ft5Sc1HqRS87mN2ry7cXhCD9g,4131
|
183
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=yf33YmWlVSjjyg0Q4OMAWvc9gjRxvttMrQBUEOfPl4I,4153
|
184
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ZWMClYN1moVRUP2f0hYac38di_pUgZggyl9d2D5rnoc,4136
|
185
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=C65Q2Mv1LxFQ_qDnv11IZ9nwl7sGZo72nWDflMttu4g,4147
|
186
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=144,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=pk6VZChh2Y0CsJSzjtUhOnlta1QLTUEWy33aKQU47XY,3244
|
187
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=Gmk24hc5lVIfQtqSa5wLOcWKedMN8aZUe93DBh6J1AY,3249
|
188
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1024,device_name=NVIDIA_H200.json",sha256=uY_XMPomaXMXxIkTR4ctU_Ybri_jMv2VvCcV-f6O_bw,3255
|
189
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=pCCKkdUzzuBVtljyk7AEIAbeDf12DUiieXaODZXzm5E,3254
|
190
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=trX2-c4N6hTTD6zFNi6A2bT3FkhxKjkM2rPl-o1K9ss,3250
|
191
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I4d56uD7E1JMXD9RAxq3FebdPquDsnNEkVaIY9Ctm9w,3246
|
192
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=sqkPi4atVPAmx_Q7KuTqsvjLOIpnJzcL6yQRIvGsJS8,2752
|
193
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=0ejgnIQ_mzJhKjQpnT-I1Vj9-rPfGlTcQ8u0cXgekUw,2746
|
194
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=lU4fjngJmpzOafi-3_q0vj2pLfZQVVagFnZNoI97etk,4128
|
195
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=ilUf76TmbtaL3W0bara6JIBEiV_iPIs29UjLbH_GYtc,4145
|
196
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=4ye1VakIIzrGUTxGNb_DM5v59djLgok8SeBeU_YI6Go,3252
|
197
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=G4PKqWxh0MlBhg7QHKj0m--_fP3Ll0gs7VJaeg-NIDM,3254
|
198
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=bKX9AvcxN6k-i3RUmHSchZZ3rjoYRYb4iBqhCI4L3MY,3257
|
199
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=OeJUCPVBD1z9CSooZpy3hRyAasjKqFAQaTLcWK6PWno,2741
|
200
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=OiEXvxm5tmcbrEtSIWlS67x-4h96gDg31L3sPjShnEo,2750
|
201
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=cGVjKx34AJRE2LGY_JWwpwS5gBqD9_c9T3xe0pUMH9g,2914
|
202
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=cuw9Htez46GkPB8TPtCDiJGhGSpAfqA4-UmLy32WHFs,2739
|
203
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=Fo1glFnfnYQOqNvk8Kau2WP90iO6zTZ36iG9MrlbPU8,4150
|
204
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=xOQj9y9CQFRCRBZ8G9RHMw03PrCNybpcXRU5sME84-Y,2911
|
205
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=1YsFa5ID0jTHIxOGpkt8VeDzhF9LpyATfQry_ikSDVw,2748
|
206
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=FGVvsvw23DeDFLj7TNqm402fAtib2cPGRZR3ePBeUp4,2753
|
207
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=kklgf2qLI5CQYiJJ5e9Gxx2gAfGxcyMDYpdJnIXPV8E,2748
|
208
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=8e0tN_DHPwvh_HECVHx9oOF_4WWdaht4s6Nmd_K-aBU,2904
|
209
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=fRzKfVFIcnxqu6DvGJQNltuFRRGz8F-eaL73bIzBzo8,3255
|
210
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=20,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=zq1x3KwZ3YuzE42OPPsElXT_VS9sK135CdB1RsotLU4,3252
|
211
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=24,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=lJbEa7VsBVKL_iRoHniB-2nceMrPctkqtjKszPnX4pk,3248
|
212
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=RuUDK9XfgXs1eZESWQR9ba4tu-rCRG_UCYwjaJ568sI,3264
|
213
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json",sha256=wlCi9aoYp7Zc1GThEutvWDbse0kKnNaQgFJsd_L8be0,3259
|
214
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=tPYxeo_xUOkjQrZMdf9v4IaFrw0RGaZNLGLJPOhjE_g,3260
|
215
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=MW7KzNa7DcKm53u2Jh-mnb93A3ICefgQHkdKONJMfew,3255
|
216
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=0aSYzpv_cBAlpWCPrfGgNTCfae1KdKQnT56E8XFQl7A,3262
|
217
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_H20,block_shape=[128, 128].json",sha256=JEOXj48phwoumZWBwNq9TpqxVwIrbnfot4QfAdzvLJI,3249
|
218
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Lqom_VMIPduSZTZQdeL2Wl_x3r9q6RmI9bojJrYwQZ4,3255
|
219
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=XmKFaMheq7NNrsvYCJteul0w809l_l460ZiDQC9ToGs,3262
|
220
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=5ro9O8Nf-7MB8NGCQ3QV5kB2k3iSWe0rdTz2A4W72CA,3732
|
221
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=5ro9O8Nf-7MB8NGCQ3QV5kB2k3iSWe0rdTz2A4W72CA,3732
|
222
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=23CJv3de1UDX3EduMpylD9AA8qL5kzMSjLK4GDMqlro,3734
|
223
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=IMTKnPRjhSptf7smIkpqmMjSML9SQ7I8CpkbR3Inzqk,3258
|
224
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=yJzHX8nNWnKwj9M8281dwwPhOHQ039mBpvNgG7poy3Q,3264
|
225
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=R4B2n2vGt4pPo6jS4Bmnx8AYtcfF9qQJE5bD7OhmXHs,3265
|
226
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=Y4WpmVGlGERHoeoQNGkQ-GC-MsEtMblqnAVuDbARJdw,3240
|
227
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json",sha256=RUkd9fW9WbajF_fFIzppsE1qyWGR5aRC4Cln-BPdu28,3254
|
228
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json",sha256=Sc9xK1wtRUqIzXppbutcq-Y2e9M0DZl2OGVzzB0aQuI,3265
|
229
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=TBscr1uWwpY0FrKQ5Y3EO_Qg6I97u4f_zjnWRvoeLvE,3260
|
230
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=6QPLhZurIqcMVdy3w0Dd7gLViKxsyJRBz-qd8agpi6Q,3248
|
231
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=uv-RwTNZT2n264dLo4eWxUpB3g7QqUyf2MFEGiRvoqQ,3251
|
232
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=XbCRIOmiNqVKh89p-0UxvvspINRDA1iV83f9l5yORwA,3254
|
233
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=4uQnjGPWokscrxiXDIvexOA8OkK5vkoIulmvvMFIEog,3250
|
234
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=i5AXj26mWI-xEoOnLCZDXUzz8jk2RjDcGuaiT1QYSbY,3263
|
235
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H200.json",sha256=fJKk5LEM_LSnq1yc3ekLqAfbUWzPojQA6yX3XgSFo-o,3254
|
236
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=iJVlnCYTNDMb6U1UnV46ZuL_8LcpOv_XFaYWIeRFeNA,3263
|
237
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=KfvSYCMG48vnRb35d9WOxYyZulI-RBrUGXUHQxXi4hk,3264
|
238
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H200.json",sha256=60yuOluuk6q88Ze0toPJB8hzMBvF7ZWyMZpriMdQf3g,3252
|
239
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=DA4PrCu_BNLSWWVTwOicNfbyqUNW7BTZC2dyFz9DVbU,3265
|
240
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=prj-QxdfS9Ns5WRPvahY_Tr7CyqlaVgNHPT89SS5zzg,3239
|
241
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=AUgoHK1PmAFehSNmsbxunlBdzM50Q5nFvdnG9FSOjOw,3265
|
242
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H200.json",sha256=pC5fdtEFc5aVNzpj_REHhz1QPrGvgI9iQCvlodDP7J8,3244
|
243
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=yZ_6KgwJvKPGblpbHPQvEMcUc9F7G9A0mSXHfgfztgo,3263
|
244
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=oxOKFDrgmw1YmgxTtRa1uoe3p09ylTLrkj_jOTqNh1Q,3249
|
245
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=bfr70r6PmM95w7raabQOaOOSPiwU2OQCOZh-kKXIehY,3248
|
246
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=4g9lABUJnB-iVwXfYPYcI05XFPG4jY8o0yJUK7kSPZM,3253
|
247
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=RGLqrAGvPCFZ0jMPBCJ0TqsnrSdW-EbUaSZu61cWGN8,3265
|
248
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=sjEVPVTgUAlp4s8tZLGSyeNzbW6zTtUm2IioH3nZsIg,3254
|
249
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=eD3Y9sOwHFcgVdOfya8KxPhvLx_b4whfEWm4d8Y2HW8,3268
|
250
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H200.json",sha256=KIfpZydSl31FOEqq0EBfxTyWRj1QTDwTjkPHFjNO3_A,3253
|
251
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=AMD_Instinct_MI300X.json",sha256=Hh3sfBOR5j3Hz9O2yoOw56A8KAYZabqWTr1uXem4vvs,4733
|
252
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=AMD_Instinct_MI325X.json",sha256=Hh3sfBOR5j3Hz9O2yoOw56A8KAYZabqWTr1uXem4vvs,4733
|
253
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=AMD_Radeon_Graphics.json",sha256=Hh3sfBOR5j3Hz9O2yoOw56A8KAYZabqWTr1uXem4vvs,4733
|
254
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=V_sgDtEtGEuBsGVa0maYJHhhGqe1NE7l-1ek2ed9WP8,3082
|
255
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=LD4Z5MRR5Ivi4bYB5hMgymtvmFyVJwq6gmehA7fzecc,3271
|
256
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H200.json",sha256=GLIH4egg-pE-NWU5XqKuJCoRXciHN6GSc3NaE4PaeYg,3261
|
257
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=AMD_Instinct_MI300X.json",sha256=zcNvXyWveWBefuCTviItdnkFAUi3ou30PHpkktwodQM,4730
|
258
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=AMD_Instinct_MI325X.json",sha256=zcNvXyWveWBefuCTviItdnkFAUi3ou30PHpkktwodQM,4730
|
259
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=AMD_Radeon_Graphics.json",sha256=zcNvXyWveWBefuCTviItdnkFAUi3ou30PHpkktwodQM,4730
|
260
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=AffDc0_51ML8HiA3757zbD10TZJdUsUDIYIqO4g0yUw,3250
|
261
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=IEYBNjt9HGnzoOVSWvL0A0jUqq926QD0_BvVYR4RA1Y,3252
|
262
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=Ns9Y12aZbJnFhcG3nwb67bDqqiQAo9tdTAIe8K2Ajz4,3255
|
263
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=obNtHlqs6l6EBqGm0e0TD2wR9TYoQV_N9Y7om847WJk,3268
|
264
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H200.json",sha256=juxJYeWYFHeLb-83_IDgrHEpoeSEursjXD43mTHBdLE,3246
|
265
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=HOxWmCI2ifHmWc0or2y8nEen86jDeLDov1-tuMzuhxo,3256
|
266
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=csHezh0HGWaNwrblGzMgcE95hqbqjWS8HImLRJYr_ts,3266
|
267
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=_5weLBinQCDzyV75hHKIT95Y0ce94KWft2_5BC6EkbQ,3254
|
268
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=4O4VeMpgFNrqWyWqWgYgcYAgBQnOlAXvt26CRSXK-sY,3270
|
269
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H200.json",sha256=qfjbXqbl902TuiyzzomUy2sMvs-Dud8ZphDRY5WIPBM,3260
|
270
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=AMD_Instinct_MI300X.json",sha256=ZnslvT6HljcanWwYjF8nthwqr_h4tjyb_wELBdcGD48,4732
|
271
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=AMD_Instinct_MI325X.json",sha256=ZnslvT6HljcanWwYjF8nthwqr_h4tjyb_wELBdcGD48,4732
|
272
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=AMD_Radeon_Graphics.json",sha256=ZnslvT6HljcanWwYjF8nthwqr_h4tjyb_wELBdcGD48,4732
|
273
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=Ru460ZgnUP4U8OsJfwF8n-AI-gfcolNR3_qzoxG6DtY,3254
|
274
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=K6BGrKw_oHTAtHjsZldcjp-BUM1dIecKXrrRn9OpRGs,3254
|
275
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=4Q_-yITMfijOMoguUM2n96clARh-DUFsS-4oW_a3Jpc,3252
|
276
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=qqFoMaObuO8pFWcSb9q0wYsdC4eSCO7B-_ruQhR1N9M,3264
|
277
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=-5nkLIunjG1ghPoUEtt2AXEQw9oGiilP7K3UvQv9CqE,3252
|
278
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=BXjSVGdvgP_-7xTvbHOO6ZrXWe0qSXiQChxoHGgWL7o,3263
|
279
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H200.json",sha256=Pi2coJlJlpgqXiPRd77B_eCmmi7sCdBuoSGK1RA5YO8,3258
|
280
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_L40S.json",sha256=p2qlRhTt7owWB8keEmoCrPZpo39IAxsKnULFQ7R38SI,3873
|
281
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=hdWYpkBWfG9kwUYco1VNjwU_S65Coat1uzfEJl33UfY,4409
|
282
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=hdWYpkBWfG9kwUYco1VNjwU_S65Coat1uzfEJl33UfY,4409
|
283
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json",sha256=hdWYpkBWfG9kwUYco1VNjwU_S65Coat1uzfEJl33UfY,4409
|
284
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=DxYu8regZOSFu8ugFGA_QbwWK4g8xwQUZF9a_nNY4Cs,3255
|
285
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=obzfE_9XgsbFNfC9biYOHxR-V_Bgc7PKT8qZZJaiJJc,3262
|
286
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=qwKy8oaMsd3QrXgQbM_x9xcfYiHK_Ou1CEwDPL5Gbgo,3259
|
287
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=rR8b-OuQ3watb8b2zuNlxKDSZpzlAagm9nb-FdKkt7s,3270
|
288
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H200.json",sha256=8G_QqV_DhvZ6xSavMSpeE6qcXPVpsVjEtJabydybKqY,3263
|
289
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=AMD_Instinct_MI300X.json",sha256=hW48t9J7ptdtil6MKMSfXV-HQ8Eba3SLOgScNuwseSg,4733
|
290
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=AMD_Instinct_MI325X.json",sha256=hW48t9J7ptdtil6MKMSfXV-HQ8Eba3SLOgScNuwseSg,4733
|
291
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=AMD_Radeon_Graphics.json",sha256=hW48t9J7ptdtil6MKMSfXV-HQ8Eba3SLOgScNuwseSg,4733
|
292
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=BAJnXTZoewwCtzJLUPJ0oYuALv640MvDuLseGcsYaaw,3252
|
293
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=-Tj7ImS6ZFDof_0VTyq7kVm8XD9B54RD6CUOPSf3Jjg,3265
|
294
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
|
295
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=3YQakSmUKhpw1KO7Hn-tEc-yyD1fEj01_6JlSYnrrlI,3274
|
296
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H200.json",sha256=W2ka_U8pzwjzX62NEGKXR32uuSR_zfHD1XjXYf5bgBs,3262
|
297
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=-RzUWSIAAsg6iA-8SPMa68hPpBVoUyMJs3dLP7edRu0,4323
|
298
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=-RzUWSIAAsg6iA-8SPMa68hPpBVoUyMJs3dLP7edRu0,4323
|
299
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json",sha256=-RzUWSIAAsg6iA-8SPMa68hPpBVoUyMJs3dLP7edRu0,4323
|
300
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=sY2nWMPh9lsIkhPCjkHO245wpnfFbrHmzdcZDVFPVww,3265
|
301
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Uz5X80VcNBOaxshwVNUEittHk2zqB4HQCfTJ4TPG5aM,3274
|
302
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=T-_T-oW4qpjTIBaGVxukJksRE7Yg8m9HNHgJ2XmR3aI,3242
|
303
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I3k416HbXU_rYb8scD8gAI4fuBlElHl06PM347Qa11w,3253
|
304
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_H20.json",sha256=RgV8C4F1LO09h01YsgF_eqX6GNoBtC7ulPfJRUUbg_g,3241
|
305
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_H200.json",sha256=nsNEuDNks0tVLfQfIm7xxFwEeptTfQcoa9fJy0NS8xQ,3247
|
306
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=R4gBc3sMY5QwOtcGwGKdk2Ak4UsUbBd3jDUeKKk0O1U,3257
|
307
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=qbqjisJ4oKmcYzumHPRk5UyOzsdi8J6xas82UWHMeAI,3263
|
308
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H20.json",sha256=vS2DRIDOqWyiBvbG6H746ownfkD1F8Aj2YZ0ET9xll8,3232
|
309
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=1n5XyZZ5sKAi-Z1duWOhLUfr6gkvnOpvxfbqIT6iU_4,3265
|
310
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H200.json",sha256=xqhl748it8GV2KXX0XixitE_ywnsKksqK8AGL7tAgT8,3254
|
311
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=FsWbV4Q6AzAtgegVuENBDz2ZcSJsqNiwUIVfQbpP7hQ,3244
|
312
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=T5rXJOZYNEs_3hE8g3ch802DnySbNiIqdn0s0RlJr8U,3249
|
313
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=9L5C8VcSsiUr5XryXB1AO3DknlAQowp6DU6S7OSzEA0,3248
|
314
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=IuvyC8TNhCVAmUZfLSoETsyCKsmejKXrs_0zuwFLPAU,3265
|
315
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H20.json",sha256=10Ntu2aVD5vGLonx-jW0qNw-tgZWdZmzMGx7utDVeng,3237
|
316
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=pdQ1RvXvdWDn8Y8-8MAX3vn-T-wbtkZvHV9GZZvNjnc,3266
|
317
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H200.json",sha256=JraM-Nvbg5V_TJkSl6UPFYZN1zHHoIbr2pAcksenoTY,3248
|
318
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=96,device_name=NVIDIA_H20.json",sha256=JtcHRlPz8xQEAqJ9EWI63oYvdmjQFG6VTHqtt85VOSA,3221
|
319
|
+
"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",sha256=ttFuL1rKnEpShItmlGyClOfpUwLi5cZYFaVgo7CAxnA,3268
|
320
|
+
"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",sha256=Pc2ri-qDByslfD8LgJtRB9QDWjI-KqMeA5ftltiwy8k,3262
|
321
|
+
"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",sha256=uuua9V6-1H38ASMPQ60t7UOtV0IQLZWBCl13MwQ25Ss,3264
|
322
|
+
"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",sha256=f0PAo2Qrrje7BPYyqB21az-Thyy2zChtDtTfAFken-U,3263
|
323
|
+
"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",sha256=BCO-cUjAG1eE9I_9LoiStHUz8dEQYpjiPzHtTXXyLF0,3264
|
324
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=7YmtaXKnmX8DdYnUJ7WQFa7xjr2Yun9WIdQNoCf_K28,3255
|
325
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=8gNamin6OqMiQ-LMVe4yQBo9ONioiC4loSWPnKcS1XI,3262
|
326
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=3Zt4hbC3yJxWvP0T7K93YAPaUP8fQ1P1Wk0CGqtBga8,3259
|
327
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=P8GpVR8fjrX7OFbBBFE4y4MJ4uhgoyUV4NYCm1qhWxk,3266
|
328
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=4B0SmzRQ2-PsBJcFe7neM1OKfWpsbiY4x6c6COQNMsQ,3254
|
329
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=XyiOCufhAu5BCMHoW9q4gLSRQEGd22bJnJkw15MqFYg,3267
|
330
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=f5HTi_9fWvInEyJp8pFgaVN6A9vxu3_845eSZGN9Ypo,3264
|
331
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=Piw4LN6d8QYrUahWsw3XUOtTMD1o3vHPwA94sGI56Gk,3242
|
332
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=3T8_rF2PEojhgTMyQ8DscXgJCWWdWfDPj4M434zWcA4,3243
|
333
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
|
334
|
+
"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",sha256=fo1akCuGoqcGwQgfh56hApgg-wLXfo9kHHksE_6m1F4,3262
|
335
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=a9XJZ0XudUTebAdN5guVq-3XSvZetHIRjatO1-_0xCk,3257
|
336
|
+
sglang/srt/layers/quantization/__init__.py,sha256=isMl8LINJFMzEse4r2Ta_7JXT15eKCX4mDIikuwticM,12559
|
315
337
|
sglang/srt/layers/quantization/awq.py,sha256=KemDG55U3B6YZVjMV71awVAIj0islFvtxcUHmOBeGy0,6739
|
316
338
|
sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
|
317
|
-
sglang/srt/layers/quantization/blockwise_int8.py,sha256=
|
318
|
-
sglang/srt/layers/quantization/
|
319
|
-
sglang/srt/layers/quantization/
|
320
|
-
sglang/srt/layers/quantization/
|
321
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=wtgunvlmuYg_6wEA1_rd5BHRhGlWDmIRq6mIdpb5FIo,20234
|
339
|
+
sglang/srt/layers/quantization/blockwise_int8.py,sha256=vWyPZsRLhdKtSmjvlT5fsowBK_nEebYbDAUh2yqseGw,15285
|
340
|
+
sglang/srt/layers/quantization/fp8.py,sha256=Odr96VvYrnPhJR-bH7_JZlduqd_6ikihjZQ1EhoGuQ8,44474
|
341
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=pUda_glnAprnFIj3VUgCUYMKb2-uK3UOC3yPahgRMBQ,34743
|
342
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=_90Js9EwurcSKIr69_6avEXbX3--Nd9LicRkRU6CGts,25580
|
322
343
|
sglang/srt/layers/quantization/gptq.py,sha256=d1frUjvXmZfQKkcMQY5t0BA4sXWHE9Jze24qxniptJE,26719
|
323
344
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
324
345
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
325
346
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
326
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
327
|
-
sglang/srt/layers/quantization/moe_wna16.py,sha256=
|
347
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=P8k89x2HeOCNWTqlHfHMIDL3g1Jv_32HiSEh2tblKh8,28744
|
348
|
+
sglang/srt/layers/quantization/moe_wna16.py,sha256=PBgcQULe9oD2i96BeJRZtIdIUkWzS0IWU9ev3C-h7mw,19646
|
328
349
|
sglang/srt/layers/quantization/qoq.py,sha256=adhsCixRUTh1m8sfpRWNhh5oX3I1WJli3Elg8uexP6A,8222
|
329
350
|
sglang/srt/layers/quantization/utils.py,sha256=AXvGD8KRZVVrkRR1Y64fGkz4lkUP-CAjAQdp0LDNXrE,5266
|
330
|
-
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=
|
331
|
-
sglang/srt/layers/quantization/w8a8_int8.py,sha256=
|
351
|
+
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=ZB6ydquyPOORDe9OCoEBRH6dsQhCeRWv1YIgm8UDQwQ,11622
|
352
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=_BG6Zo4tis0UGZ47EVfBmfpOxRKzXvd3EM15qDWy7OM,9147
|
332
353
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
333
354
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=EaOKuIA0zXwqmH_eVhWeNdGJT9d1d9gVvFyYkgpdjDg,25665
|
334
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
355
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=HMON7sPz0kfG5f7cDbPtup50Xc8G_nIYzTB0Eyc8-gg,26460
|
335
356
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
336
357
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
337
358
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
@@ -489,12 +510,16 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
489
510
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=PD4AJYCkHfy2ivv9baMouFXzBTy0eKMumbAfxfm91HI,3256
|
490
511
|
"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
|
491
512
|
"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
|
492
|
-
sglang/srt/
|
493
|
-
sglang/srt/
|
513
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
514
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=BrzCCxXtJJHXMmKlo9nm711ZB-yO4uGw4PJLdnY_qqw,11527
|
515
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=zkMzBAqQTSwG9TlGPuwmHV1yN0v5Y_5Hgyo0CKQDVNU,741
|
516
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=On_uvP1ThxgQFAzOWKoteM0vIOHqmtI127A4qbPtmbc,3264
|
517
|
+
sglang/srt/lora/layers.py,sha256=FaTYf0w3zbKKKAT1nJdAzGRtxvySB6FpNKXvEi5RHH0,12958
|
518
|
+
sglang/srt/lora/lora.py,sha256=WY3cISWrQ5Ye3YcNKJUwAWRImzlpLQva2fGepg6P5EY,9744
|
494
519
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
495
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
496
|
-
sglang/srt/lora/mem_pool.py,sha256=
|
497
|
-
sglang/srt/lora/utils.py,sha256=
|
520
|
+
sglang/srt/lora/lora_manager.py,sha256=8DG_TJQeHIGXLjSxJt7nFIaEQqgQKjdR4HwbokwDntI,13708
|
521
|
+
sglang/srt/lora/mem_pool.py,sha256=lLmKinsTK3rWTNLJSLSSwKJud98z4up2Lsnb2b5H3ts,10007
|
522
|
+
sglang/srt/lora/utils.py,sha256=3UwpyNONBW8X-ycgDV1lvVD3w_v1mVIs0T2wpVWVe7A,5484
|
498
523
|
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
499
524
|
sglang/srt/lora/backend/flashinfer_backend.py,sha256=el6IAB4kTgDTbwCggmqFuukliyoapN5X6FLksG-4wJ8,4151
|
500
525
|
sglang/srt/lora/backend/triton_backend.py,sha256=uqwBGlguXX8EkCKjSPqac6SPTgcKA31u3u6HkKPQcos,2530
|
@@ -503,85 +528,91 @@ sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=vOUDzC_Sq7UGnDbdF8F7ChKG12hD
|
|
503
528
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=qCpJAksCSXS3Znm-ABx1QfrdNqj9hrP61oaeW-n2RhU,5945
|
504
529
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=yNBgl8jS76DPlGJg8puRkSnKkewf2_2oKfVZZRq4lYY,4351
|
505
530
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=EoF9HymgQ1V9DwyOJOvbw1hCbEjprVOne_fC4VHgj-s,4518
|
506
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
531
|
+
sglang/srt/managers/cache_controller.py,sha256=jv2-YkXRc032wnAoTQZMhTUzHrAjqSvdlYOSaWbbHr0,18483
|
507
532
|
sglang/srt/managers/configure_logging.py,sha256=fOJaXAQ1n9m-8KPJndpsKvS885i69SMafoEADLIVfIM,1633
|
508
|
-
sglang/srt/managers/data_parallel_controller.py,sha256=
|
509
|
-
sglang/srt/managers/deepseek_eplb.py,sha256=bExIzjdX8IcBOWYdgne5n0VV9Vht6AfDPeBjQY1rttA,10699
|
533
|
+
sglang/srt/managers/data_parallel_controller.py,sha256=PZ-wOcAFn3PQqMB6I2vjIsFmplf0nlNl5hqTDKTHTG8,12112
|
510
534
|
sglang/srt/managers/detokenizer_manager.py,sha256=SpLxTsSPKBZfD-ZMhJ5zpPPGuUb8PmcYgFSL9CsurU4,10696
|
511
|
-
sglang/srt/managers/eplb_manager.py,sha256=
|
512
|
-
sglang/srt/managers/expert_distribution.py,sha256=
|
513
|
-
sglang/srt/managers/expert_location.py,sha256=
|
514
|
-
sglang/srt/managers/expert_location_dispatch.py,sha256=
|
515
|
-
sglang/srt/managers/io_struct.py,sha256=
|
516
|
-
sglang/srt/managers/mm_utils.py,sha256=
|
535
|
+
sglang/srt/managers/eplb_manager.py,sha256=YaxnvD1-wMV7BhtF9AxoNRVsJUdlQzFF7N-JDP43ojE,3411
|
536
|
+
sglang/srt/managers/expert_distribution.py,sha256=HBcfNdS3l6ob17Z9KFlX5f79rqcaY41XMDp8emMD-TY,30880
|
537
|
+
sglang/srt/managers/expert_location.py,sha256=ZSsH17k5bAgbE1wuvpGaHGueiyhfPrgQakBFPu9jswo,16669
|
538
|
+
sglang/srt/managers/expert_location_dispatch.py,sha256=U6-XLZ77RK0oy_JUVug2q-2LJjwoYX-js0_zhBNMXuM,4148
|
539
|
+
sglang/srt/managers/io_struct.py,sha256=Bpxxn8ht8Q2T7jLEP5M8TK2_Vgn9XPWKvEz6V5yVX_s,33420
|
540
|
+
sglang/srt/managers/mm_utils.py,sha256=mA9W4xZBnXfs-4ZeALvhdpGAYxrJGfOxBWyoHVrt44Q,26518
|
517
541
|
sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
|
518
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
542
|
+
sglang/srt/managers/schedule_batch.py,sha256=2aKod4fNwHayeU9V5M9lFgiY2hliqoeWMPPSauo-Hpo,72438
|
519
543
|
sglang/srt/managers/schedule_policy.py,sha256=6uRRgxbTJ0pztoAg8oRh2u1g6hNejDyMevD2-68zEYA,19723
|
520
|
-
sglang/srt/managers/scheduler.py,sha256=
|
544
|
+
sglang/srt/managers/scheduler.py,sha256=Rq2mVboJha7ce0iGFG6xVjMIn-dyj75QMlIoUnuKf88,104546
|
521
545
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=aaj0z1PD3fGIOPoTtWwqoKsii0yQCR7txVFXMPECveQ,29879
|
522
546
|
sglang/srt/managers/session_controller.py,sha256=Lh1kruMcKqR7WVWYJRZbYgowtsssVlP7_paIVXLLIcE,5756
|
523
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
547
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=NcDNtH_7Bg2QE_v7YmNWDeLcaWFkEn4b-kO7i5KrTM4,65330
|
524
548
|
sglang/srt/managers/tp_worker.py,sha256=cnI2JRxDqM7RXaaXAnLHNyYH4Jt7SB6HLAD5fRoWoNA,10025
|
525
549
|
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=W-FP7dkR9_voS0emMj4N5ML3Iao9gNZc-on6iUflbrw,9835
|
526
|
-
sglang/srt/managers/utils.py,sha256=
|
527
|
-
sglang/srt/managers/
|
550
|
+
sglang/srt/managers/utils.py,sha256=9_VGE48EK0PXVJ26aYvbRJ6n7gIZALvCcf6uZCccCgM,1369
|
551
|
+
sglang/srt/managers/eplb_algorithms/__init__.py,sha256=wVUv2ZhhC-_VbLaStpk3vulzhqExwfHGZJQqoohs-Fw,1963
|
552
|
+
sglang/srt/managers/eplb_algorithms/deepseek.py,sha256=mMZT7zAAArccdRS0xXxifvMb3qn9enSt426uUTKeiq4,8340
|
553
|
+
sglang/srt/managers/eplb_algorithms/deepseek_vec.py,sha256=Vzy5Iarua1VgVHzjBNZaVV_vt1LY1BLtJz7PmzB701k,10654
|
554
|
+
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=DQk5qNh7MDY9DQoASiQbCTwRb2HdvLWobzHmE0Ni_fg,21500
|
528
555
|
sglang/srt/managers/multimodal_processors/clip.py,sha256=lRc2mcuDbAhZVf-0EfkO81pqDiol9zLvTpDqtPIBQ2k,1525
|
529
556
|
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=CMfhhdq7u6GzT8ZENo7ByClvQEx-HKaTGVgdYM1vMNw,3460
|
530
|
-
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=
|
531
|
-
sglang/srt/managers/multimodal_processors/internvl.py,sha256=
|
557
|
+
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=oBHXlbwto_84ZkjkW2A7F3Z7kNuDf039uDH4HVXKE1s,2290
|
558
|
+
sglang/srt/managers/multimodal_processors/internvl.py,sha256=ASv3MQ0Ju6oZG7UceS5ziy4rL2d8Xf1_LbIFmEAuz2E,9512
|
532
559
|
sglang/srt/managers/multimodal_processors/janus_pro.py,sha256=nSZYKLoCZtv7sQIM21KCt4jpnzVfcsF84m9CFPWwR7s,2058
|
533
|
-
sglang/srt/managers/multimodal_processors/kimi_vl.py,sha256=
|
560
|
+
sglang/srt/managers/multimodal_processors/kimi_vl.py,sha256=8DER6QFDrmD0sZMjlAffY4z3jtBrrIYoU8ogpZIKNio,1868
|
534
561
|
sglang/srt/managers/multimodal_processors/llava.py,sha256=90D2A09EHgdWwapVSeLg5J4YsioeT2AvGmJkepZA-5I,8100
|
535
|
-
sglang/srt/managers/multimodal_processors/minicpm.py,sha256=
|
562
|
+
sglang/srt/managers/multimodal_processors/minicpm.py,sha256=y-1UHmXq2bmDtTax2b-rJf-CI478MMpoz9nY3b-OKzI,5561
|
536
563
|
sglang/srt/managers/multimodal_processors/mlama.py,sha256=MLiGS606LzVtdoXvjWGANx-K_7nE9J_fMVmkXN7Gz8k,1661
|
537
564
|
sglang/srt/managers/multimodal_processors/mllama4.py,sha256=IAu09ZPMAHxZKsfGiKjZU_Fruj4AmKA0poqXC0zufWQ,5813
|
565
|
+
sglang/srt/managers/multimodal_processors/phi4mm.py,sha256=-yTlt2kQkrgks2IzaRKmEj-7siAvTDhZHDR_J3NVFdw,2610
|
538
566
|
sglang/srt/managers/multimodal_processors/pixtral.py,sha256=uQJYbxhafNCmg0xP52FdElnkUatAyintER1XNuKz3b8,4195
|
539
|
-
sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=
|
567
|
+
sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=RLv8sBuKhAjeaVqrFR7hwEEw7fX1WOMZ6r2R4gFeV04,7025
|
568
|
+
sglang/srt/managers/multimodal_processors/vila.py,sha256=AeQlhdIKKoN0lre8_zYQ7YpGu7I_rux1bRLt70sPKJ0,2594
|
540
569
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=WOUIY6ATzltzXQ7QXS9biSY2o_kzbpDIuTD4C6TLCQQ,1019
|
541
|
-
sglang/srt/mem_cache/chunk_cache.py,sha256=
|
570
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=vcA-BI2MwlTiPHrzaufQKg-uYPvpeoizAI4bvv8Ie0w,2045
|
542
571
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
543
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
544
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
572
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=yw-vSz1BBMbjsw90k4i_XAwtlLm6ff-DL0bvEvTbJeg,16671
|
573
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=6qAHD-SLLYbOrJTIqGjgXBE577uwJrFvGknaiBHWzYI,26316
|
574
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=9N34Y7P0aM2xkmhsEw2_W8xN897h-HEwzRPIu1REwac,13186
|
545
575
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=Q-lYcI-3HoLu0WJhE2F_An8g9mkZ8LwMrYnQ4383Rf0,1266
|
546
576
|
sglang/srt/mem_cache/paged_allocator.py,sha256=BrJS0vN1k-vTSgb_M8u_1KoZFRgzgR1WRyImCTq3T0U,9770
|
547
|
-
sglang/srt/mem_cache/radix_cache.py,sha256=
|
548
|
-
sglang/srt/metrics/collector.py,sha256=
|
577
|
+
sglang/srt/mem_cache/radix_cache.py,sha256=CeDEHnfYONX1Ra5QKemcs06RHzkDa8oV4ZaqHCayGI8,17699
|
578
|
+
sglang/srt/metrics/collector.py,sha256=C9QEJDOEdOPBwy2IJwFS3R6VbGzVzGs2xakKCCPvQDk,19903
|
549
579
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
550
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
551
|
-
sglang/srt/model_executor/expert_location_updater.py,sha256=
|
552
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
553
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
580
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=XoChArN7oF-YRApkZwiHHWRY8qFUpFPQ2o3k9K5zuJY,29279
|
581
|
+
sglang/srt/model_executor/expert_location_updater.py,sha256=HWLY5lJAWefy2tobWJKlHs3qlBSCS57EwSMdfUuPFc4,20585
|
582
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=zMT-foMHqR51bHZ2qj3KpWjJqDL5cfy7997mhiIFz1E,28848
|
583
|
+
sglang/srt/model_executor/model_runner.py,sha256=1TyEuSOAwr4AMjtutCa2eXijcrK8Pe3-FlmXVcG9xG4,53496
|
554
584
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
555
|
-
sglang/srt/model_loader/loader.py,sha256=
|
556
|
-
sglang/srt/model_loader/utils.py,sha256=
|
585
|
+
sglang/srt/model_loader/loader.py,sha256=JNhJrnCNCXTCroD5FKJdiBr8Dn4VNtTQ0XmqfkPI21k,56002
|
586
|
+
sglang/srt/model_loader/utils.py,sha256=zSZBPA9ErPmkf-HfCxJjhmiFwYueB15KUg7NFspLvPY,4454
|
557
587
|
sglang/srt/model_loader/weight_utils.py,sha256=yKnau-wH9muczoCpDTCVIqXFqz-QJmEEySplX3bMJWk,32153
|
558
588
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
559
|
-
sglang/srt/models/bert.py,sha256=
|
589
|
+
sglang/srt/models/bert.py,sha256=ODJe8YfNRP-hHsomFWk4_QpcuiSsNfjzGf256EDS0Pc,15802
|
560
590
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
561
591
|
sglang/srt/models/clip.py,sha256=mkdSNhc2SgRHyeq9tCLEjUGdnA8yS2EMMbMKSpn5dMs,19863
|
562
592
|
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
563
593
|
sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,15598
|
564
594
|
sglang/srt/models/deepseek.py,sha256=ZnN02HdgXCB23Vno5V9UMUoOxH5HC82vNTwsVulUJ-o,17206
|
565
595
|
sglang/srt/models/deepseek_janus_pro.py,sha256=OeeI7vZbE4HGpxa8CwT6-Lbfs7J7WMQ3oBNpVJQpv3w,70450
|
566
|
-
sglang/srt/models/deepseek_nextn.py,sha256=
|
567
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
596
|
+
sglang/srt/models/deepseek_nextn.py,sha256=2ziyjv_QEeT3lGNgxG_F-vcAT-K5p2hiz7VEimBgzLc,5675
|
597
|
+
sglang/srt/models/deepseek_v2.py,sha256=TD9E-60eu7jlEqdW4nT1FQS5x03HzSVxOhhCdGc36nI,85363
|
568
598
|
sglang/srt/models/deepseek_vl2.py,sha256=j8BdxZsMjm6lPdbDipEIKhVIVywCP1Vl1Kl46BZ5_0Y,13147
|
569
599
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
570
600
|
sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
|
571
601
|
sglang/srt/models/gemma2.py,sha256=kqtwdo93GWKm2iBN29RoIRH2ggRm-K_80LM5btgfBLo,16395
|
572
602
|
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
573
|
-
sglang/srt/models/gemma3_causal.py,sha256=
|
574
|
-
sglang/srt/models/gemma3_mm.py,sha256=
|
603
|
+
sglang/srt/models/gemma3_causal.py,sha256=Vm605KeF7CBXbtxzOWF-v0TLbl0G12CLF-bEgTV9T0E,25197
|
604
|
+
sglang/srt/models/gemma3_mm.py,sha256=b9YmkipsfVb5IXVeIVwW_PviXiCkRULhEsqNOvPoDxU,17221
|
575
605
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
576
606
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
577
607
|
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
578
608
|
sglang/srt/models/grok.py,sha256=vESZeGS4adI_JAerXIkCcTm15-CNiGeS7VHc36C6w1A,28033
|
609
|
+
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
579
610
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
580
611
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
581
|
-
sglang/srt/models/internvl.py,sha256=
|
582
|
-
sglang/srt/models/kimi_vl.py,sha256=
|
612
|
+
sglang/srt/models/internvl.py,sha256=fZ18eKFYvvtYqoBRXKmS7KlgHMewJSAykADnrf0N3nk,23267
|
613
|
+
sglang/srt/models/kimi_vl.py,sha256=rMJezfEYaEjOaMZ7vt0rg9ZlbV9p1Ax6-kDsVWzf_bI,12868
|
583
614
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
584
|
-
sglang/srt/models/llama.py,sha256
|
615
|
+
sglang/srt/models/llama.py,sha256=qLBfL77XG3pI-UDxg5HLcgJN1tUMeWNj9-AUR4fUVGg,27144
|
585
616
|
sglang/srt/models/llama4.py,sha256=NwG0mBZQR4B6KVR-Xzp89UQYvVnFMOgkZKVWvtT7Jt4,19454
|
586
617
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
587
618
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
@@ -594,8 +625,8 @@ sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,614
|
|
594
625
|
sglang/srt/models/mimo_mtp.py,sha256=y0wTNObGz0lyVt0zu7apdVlTRLEQmc_xsd8SvgSo_vo,7806
|
595
626
|
sglang/srt/models/minicpm.py,sha256=m5HFsSJj0Po09LY9R6qj6K4gceqWDMOePz3NDGgMGT4,14691
|
596
627
|
sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
|
597
|
-
sglang/srt/models/minicpmo.py,sha256=
|
598
|
-
sglang/srt/models/minicpmv.py,sha256=
|
628
|
+
sglang/srt/models/minicpmo.py,sha256=IBMFTmak4qokNl8zBXHLYfS5slPf88ECwox6CKHbiAU,76081
|
629
|
+
sglang/srt/models/minicpmv.py,sha256=7YYWwk4LX0Z7lZegnsldctb-a9zGGgJUdjFeGo-oLv4,30426
|
599
630
|
sglang/srt/models/mistral.py,sha256=z7q5NBVbQcboQTIwhULtsLpFvNferaIv49EzOXVgh7g,3487
|
600
631
|
sglang/srt/models/mixtral.py,sha256=n-Pz7fyWE4m6Uh7sjzAYKNr5Wy4QUj5Yekl0qiCwQI8,17055
|
601
632
|
sglang/srt/models/mixtral_quant.py,sha256=-kQw9r8KcLdO8SNN9RKXzrGq9Q2Al9l9cWHi1VrZSRM,15260
|
@@ -605,46 +636,51 @@ sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,126
|
|
605
636
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
606
637
|
sglang/srt/models/olmoe.py,sha256=TMzt-yB891bvA4X50xL0NjNnFYSx9imlA7N1EG8KNK0,15949
|
607
638
|
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
639
|
+
sglang/srt/models/phi4mm.py,sha256=pX1UYlvT6r8wdEbge-FrXh1CvNA2qQRvsg594uZtcLo,19162
|
608
640
|
sglang/srt/models/pixtral.py,sha256=Iu7OTvM_nnApk1VjpUb1ucPBU2F1Kov5w6ddYn7gGqE,16983
|
609
641
|
sglang/srt/models/qwen.py,sha256=xYkVmMZS2uMqWhfndc8EYm0olpKFnggfuMp_6aobVi4,10758
|
610
|
-
sglang/srt/models/qwen2.py,sha256=
|
611
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
642
|
+
sglang/srt/models/qwen2.py,sha256=2_e20-4uKqZ8IK7_bz26SuSVDt8UD237jVzxaWIr530,19915
|
643
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=6DdLfONY3ZDSCzWFPWSR8jKwVnvJh2lMx5ZZbJy9xok,22661
|
612
644
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
613
|
-
sglang/srt/models/qwen2_eagle.py,sha256=
|
614
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
645
|
+
sglang/srt/models/qwen2_eagle.py,sha256=6spFg6JYQGeUXLv2Q5eMkVzZvnqGyvW6SdVBtFMxlTM,4806
|
646
|
+
sglang/srt/models/qwen2_moe.py,sha256=mrmEwGclGpfW-9aIRKGlvi9peecYKIE0SMvdk8Ek4Zg,23319
|
615
647
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
616
|
-
sglang/srt/models/qwen2_vl.py,sha256=
|
617
|
-
sglang/srt/models/qwen3.py,sha256=
|
618
|
-
sglang/srt/models/qwen3_moe.py,sha256=
|
619
|
-
sglang/srt/models/registry.py,sha256=
|
620
|
-
sglang/srt/models/roberta.py,sha256=
|
648
|
+
sglang/srt/models/qwen2_vl.py,sha256=A6YGktXkc9rvotLo0KcZpoUP60eUcFzoiDG65UzXZeI,20941
|
649
|
+
sglang/srt/models/qwen3.py,sha256=L-m441pSsduaayMzILrN3isnNqK7jVraUmm_6bEJb1M,14989
|
650
|
+
sglang/srt/models/qwen3_moe.py,sha256=2nOngjhOw93m6nNx0Rc3fM0Yh5lBz_GM1Ri-FCRB-s4,30824
|
651
|
+
sglang/srt/models/registry.py,sha256=bH9H0OiNV0Cn7FRBM30Oh6dxICTs9mJscdLtHYPJvxc,3783
|
652
|
+
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
621
653
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
622
654
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
623
655
|
sglang/srt/models/torch_native_llama.py,sha256=oTxxof5Wx2b2egIwWx56LeHjtPGQleQ2zM5jXHMiuOU,19293
|
656
|
+
sglang/srt/models/transformers.py,sha256=_CL0npi-_HvqzxkLgFhv2EE3bfGvCLXPYAtPFywZOr0,10260
|
657
|
+
sglang/srt/models/vila.py,sha256=DRGJXP6iSv0XjgHYIJpMzBDNYZb3__Gg_wFkmZ5D66Y,9865
|
624
658
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
625
659
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
626
660
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
627
|
-
sglang/srt/openai_api/adapter.py,sha256=
|
628
|
-
sglang/srt/openai_api/protocol.py,sha256=
|
661
|
+
sglang/srt/openai_api/adapter.py,sha256=OUXKtWrHOIsQly2KtecWo1gdTOzjCMGLHc3IXemgdjg,86874
|
662
|
+
sglang/srt/openai_api/protocol.py,sha256=3PBC8kBhiLaLvbzr0yvuE0CIKCFgnxJQU62t9ADqhVc,16385
|
663
|
+
sglang/srt/openai_api/utils.py,sha256=LL8VB-Qv9kNIVVWG1PYzoKMMHo7Y2NeVLMeJ9QEWVk8,6600
|
629
664
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
630
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
631
|
-
sglang/srt/sampling/sampling_params.py,sha256=
|
665
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=JOGU-Fa8wPtytEJ30BHg1PldeNytwy8u31azLH436kw,13450
|
666
|
+
sglang/srt/sampling/sampling_params.py,sha256=L2cU3MhAo9OvfdEtTdJidp9nTOkD6tiwlegxQ5vgIfU,6127
|
632
667
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
633
668
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
634
669
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
635
670
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
636
671
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
637
|
-
sglang/srt/speculative/build_eagle_tree.py,sha256=
|
638
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=
|
639
|
-
sglang/srt/speculative/
|
640
|
-
sglang/srt/speculative/
|
672
|
+
sglang/srt/speculative/build_eagle_tree.py,sha256=lxfaTEOTY0N9QTlgXSUae3DVtPLqW8CcYXWcHsxCJp4,11632
|
673
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=D90K4mTVsHkDYT4izKoAbJoNUzIfSTq5K01TuG8i74o,9038
|
674
|
+
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=qjEH9g0YynGakpfgznTXMm24vEhOROOpy-V6WNY7f60,9836
|
675
|
+
sglang/srt/speculative/eagle_utils.py,sha256=UuyxfbBE9DNL9FPbzyW8Fqt9LLzMq85My5RIrlEny28,42793
|
676
|
+
sglang/srt/speculative/eagle_worker.py,sha256=UOrT2Do9qvmP_gmXeJSzf8sP_sRLbZaBcIfr2cfUydI,35064
|
641
677
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
642
678
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
643
679
|
sglang/test/few_shot_gsm8k.py,sha256=qnEejCyPHGEMBEiNc7T4-t9lvoo2DNN72RXw-ei_TnY,4300
|
644
680
|
sglang/test/few_shot_gsm8k_engine.py,sha256=Yf1Dg0Tk-tY4v1oj_UTxJ7950CWn6kRMbQKDjT2Orgo,3902
|
645
681
|
sglang/test/run_eval.py,sha256=K4Z3OdMPvLeuGJhWWTBD0F-MOUFeBYLvsPnDQ44bd18,4036
|
646
|
-
sglang/test/runners.py,sha256=
|
647
|
-
sglang/test/send_one.py,sha256=
|
682
|
+
sglang/test/runners.py,sha256=AOnCXNGO9AYWrUShCDoxYajiN5yVFF9b8fT6XnwAWew,32439
|
683
|
+
sglang/test/send_one.py,sha256=XNZdfZs21tXDBwrDj2pq46WQd5smiKoYETY8U09c1Z8,5079
|
648
684
|
sglang/test/simple_eval_common.py,sha256=OW4Z7O33QqDySRFuHIC4Ouidfup4eaOEuR9i7xJzkDY,12379
|
649
685
|
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
650
686
|
sglang/test/simple_eval_humaneval.py,sha256=s8YuKIBkNUEOBP4XKsTMRdXGv5aRhl0oJyl-89lGk1w,5687
|
@@ -652,21 +688,23 @@ sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWU
|
|
652
688
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
653
689
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
654
690
|
sglang/test/test_activation.py,sha256=GeTIJHxlLQfW3kM-X1FGa8Sa3dSGKHEXl5wEy-hfGis,1489
|
655
|
-
sglang/test/test_block_fp8.py,sha256=
|
656
|
-
sglang/test/
|
691
|
+
sglang/test/test_block_fp8.py,sha256=1qBD-FJr5UaR9e5qDz91vDrS_DT1utnk82qeQ2bm-1E,21630
|
692
|
+
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7Xx0MjOoOBYL8J7ETvOVA,8180
|
693
|
+
sglang/test/test_block_fp8_ep.py,sha256=TI0TVeoX8zRDtOFclonCfgSH6vnAIOGiMKQKpf9aKNs,10845
|
657
694
|
sglang/test/test_custom_ops.py,sha256=2bSo9P5_rJZYFq8Y8IKRimDfFyZZGJluhL7Ngny0Pf4,5571
|
658
|
-
sglang/test/test_cutlass_moe.py,sha256=
|
695
|
+
sglang/test/test_cutlass_moe.py,sha256=beXdvpwpHh0O8fpLW-RV3Bx8Wu0lRFG_SNkL3Op5ITA,9905
|
659
696
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
660
697
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
698
|
+
sglang/test/test_fp4_moe.py,sha256=U4LHzpGl6pCiCZiENRPxVP6hxqkqRZ_0WXbB29vYeAo,8187
|
661
699
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
662
700
|
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
663
|
-
sglang/test/test_utils.py,sha256=
|
701
|
+
sglang/test/test_utils.py,sha256=xdi1-Fvs0ykmaYhYzC0Jx-n7nSFKSO9a6HAvWbXqVQo,36176
|
664
702
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
665
703
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
666
704
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
667
|
-
sglang/test/attention/test_prefix_chunk_info.py,sha256=
|
668
|
-
sglang-0.4.
|
669
|
-
sglang-0.4.
|
670
|
-
sglang-0.4.
|
671
|
-
sglang-0.4.
|
672
|
-
sglang-0.4.
|
705
|
+
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
706
|
+
sglang-0.4.7.post1.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
707
|
+
sglang-0.4.7.post1.dist-info/METADATA,sha256=DgH_mVdir5t4SV58Js1jZLSeJ5qB4bH0FW7aO3RfR20,26966
|
708
|
+
sglang-0.4.7.post1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
709
|
+
sglang-0.4.7.post1.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
710
|
+
sglang-0.4.7.post1.dist-info/RECORD,,
|