sglang 0.5.3rc2__py3-none-any.whl → 0.5.4__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- sglang/bench_one_batch.py +47 -28
- sglang/bench_one_batch_server.py +41 -25
- sglang/bench_serving.py +330 -156
- sglang/check_env.py +1 -1
- sglang/compile_deep_gemm.py +6 -2
- sglang/global_config.py +1 -25
- sglang/lang/api.py +6 -0
- sglang/lang/interpreter.py +1 -0
- sglang/lang/ir.py +13 -0
- sglang/launch_server.py +8 -15
- sglang/profiler.py +18 -1
- sglang/srt/_custom_ops.py +1 -1
- sglang/srt/batch_invariant_ops/batch_invariant_ops.py +4 -6
- sglang/srt/checkpoint_engine/checkpoint_engine_worker.py +142 -0
- sglang/srt/compilation/backend.py +437 -0
- sglang/srt/compilation/compilation_config.py +20 -0
- sglang/srt/compilation/compilation_counter.py +47 -0
- sglang/srt/compilation/compile.py +210 -0
- sglang/srt/compilation/compiler_interface.py +503 -0
- sglang/srt/compilation/cuda_piecewise_backend.py +228 -0
- sglang/srt/compilation/fix_functionalization.py +134 -0
- sglang/srt/compilation/fx_utils.py +83 -0
- sglang/srt/compilation/inductor_pass.py +140 -0
- sglang/srt/compilation/pass_manager.py +66 -0
- sglang/srt/compilation/piecewise_context_manager.py +40 -0
- sglang/srt/compilation/weak_ref_tensor_jit.py +16 -0
- sglang/srt/configs/__init__.py +4 -0
- sglang/srt/configs/deepseek_ocr.py +262 -0
- sglang/srt/configs/deepseekvl2.py +194 -96
- sglang/srt/configs/dots_vlm.py +2 -7
- sglang/srt/configs/falcon_h1.py +13 -64
- sglang/srt/configs/load_config.py +25 -2
- sglang/srt/configs/mamba_utils.py +117 -0
- sglang/srt/configs/model_config.py +134 -23
- sglang/srt/configs/modelopt_config.py +30 -0
- sglang/srt/configs/nemotron_h.py +286 -0
- sglang/srt/configs/olmo3.py +105 -0
- sglang/srt/configs/points_v15_chat.py +29 -0
- sglang/srt/configs/qwen3_next.py +11 -47
- sglang/srt/configs/qwen3_omni.py +613 -0
- sglang/srt/configs/qwen3_vl.py +0 -10
- sglang/srt/connector/remote_instance.py +1 -1
- sglang/srt/constrained/base_grammar_backend.py +5 -1
- sglang/srt/constrained/llguidance_backend.py +5 -0
- sglang/srt/constrained/outlines_backend.py +1 -1
- sglang/srt/constrained/reasoner_grammar_backend.py +9 -6
- sglang/srt/constrained/utils.py +12 -0
- sglang/srt/constrained/xgrammar_backend.py +20 -11
- sglang/srt/disaggregation/ascend/transfer_engine.py +1 -1
- sglang/srt/disaggregation/base/conn.py +17 -4
- sglang/srt/disaggregation/common/conn.py +4 -2
- sglang/srt/disaggregation/decode.py +123 -31
- sglang/srt/disaggregation/decode_kvcache_offload_manager.py +1 -1
- sglang/srt/disaggregation/fake/conn.py +11 -3
- sglang/srt/disaggregation/mooncake/conn.py +157 -19
- sglang/srt/disaggregation/nixl/conn.py +69 -24
- sglang/srt/disaggregation/prefill.py +96 -270
- sglang/srt/distributed/device_communicators/all_reduce_utils.py +4 -4
- sglang/srt/distributed/device_communicators/custom_all_reduce.py +6 -6
- sglang/srt/distributed/device_communicators/pymscclpp.py +2 -2
- sglang/srt/distributed/device_communicators/pynccl.py +24 -12
- sglang/srt/distributed/device_communicators/pynccl_allocator.py +2 -2
- sglang/srt/distributed/device_communicators/symm_mem.py +1 -1
- sglang/srt/distributed/naive_distributed.py +5 -4
- sglang/srt/distributed/parallel_state.py +70 -19
- sglang/srt/elastic_ep/elastic_ep.py +74 -0
- sglang/srt/entrypoints/context.py +3 -2
- sglang/srt/entrypoints/engine.py +66 -66
- sglang/srt/entrypoints/grpc_server.py +431 -234
- sglang/srt/entrypoints/harmony_utils.py +2 -2
- sglang/srt/entrypoints/http_server.py +120 -8
- sglang/srt/entrypoints/http_server_engine.py +1 -7
- sglang/srt/entrypoints/openai/protocol.py +225 -37
- sglang/srt/entrypoints/openai/serving_base.py +49 -2
- sglang/srt/entrypoints/openai/serving_chat.py +29 -74
- sglang/srt/entrypoints/openai/serving_classify.py +204 -0
- sglang/srt/entrypoints/openai/serving_completions.py +15 -1
- sglang/srt/entrypoints/openai/serving_responses.py +5 -2
- sglang/srt/entrypoints/openai/serving_tokenize.py +144 -0
- sglang/srt/environ.py +42 -4
- sglang/srt/eplb/eplb_algorithms/__init__.py +18 -1
- sglang/srt/eplb/eplb_algorithms/deepseek.py +0 -2
- sglang/srt/eplb/eplb_algorithms/elasticity_aware.py +87 -0
- sglang/srt/eplb/expert_distribution.py +3 -4
- sglang/srt/eplb/expert_location_dispatch.py +2 -2
- sglang/srt/eplb/expert_location_updater.py +2 -2
- sglang/srt/function_call/base_format_detector.py +17 -18
- sglang/srt/function_call/function_call_parser.py +18 -14
- sglang/srt/function_call/glm4_moe_detector.py +1 -5
- sglang/srt/function_call/gpt_oss_detector.py +1 -1
- sglang/srt/function_call/json_array_parser.py +0 -2
- sglang/srt/function_call/utils.py +2 -2
- sglang/srt/grpc/compile_proto.py +3 -3
- sglang/srt/{entrypoints → grpc}/grpc_request_manager.py +112 -52
- sglang/srt/grpc/health_servicer.py +189 -0
- sglang/srt/grpc/scheduler_launcher.py +181 -0
- sglang/srt/grpc/sglang_scheduler_pb2.py +78 -70
- sglang/srt/grpc/sglang_scheduler_pb2.pyi +66 -10
- sglang/srt/grpc/sglang_scheduler_pb2_grpc.py +89 -1
- sglang/srt/layers/activation.py +4 -1
- sglang/srt/layers/attention/aiter_backend.py +3 -3
- sglang/srt/layers/attention/ascend_backend.py +17 -1
- sglang/srt/layers/attention/attention_registry.py +43 -23
- sglang/srt/layers/attention/base_attn_backend.py +20 -1
- sglang/srt/layers/attention/double_sparsity_backend.py +2 -2
- sglang/srt/layers/attention/fla/chunk.py +0 -1
- sglang/srt/layers/attention/fla/chunk_o.py +1 -1
- sglang/srt/layers/attention/fla/index.py +0 -2
- sglang/srt/layers/attention/fla/layernorm_gated.py +50 -32
- sglang/srt/layers/attention/fla/utils.py +0 -3
- sglang/srt/layers/attention/fla/wy_fast.py +0 -2
- sglang/srt/layers/attention/flashattention_backend.py +12 -8
- sglang/srt/layers/attention/flashinfer_backend.py +248 -21
- sglang/srt/layers/attention/flashinfer_mla_backend.py +20 -18
- sglang/srt/layers/attention/flashmla_backend.py +2 -2
- sglang/srt/layers/attention/hybrid_attn_backend.py +1 -1
- sglang/srt/layers/attention/hybrid_linear_attn_backend.py +165 -62
- sglang/srt/layers/attention/intel_amx_backend.py +1 -1
- sglang/srt/layers/attention/mamba/causal_conv1d.py +1 -1
- sglang/srt/layers/attention/mamba/causal_conv1d_triton.py +9 -5
- sglang/srt/layers/attention/mamba/mamba.py +189 -241
- sglang/srt/layers/attention/mamba/mamba2_metadata.py +211 -0
- sglang/srt/layers/attention/mamba/mixer2_rms_norm_gated.py +120 -0
- sglang/srt/layers/attention/mamba/ops/ssd_bmm.py +0 -50
- sglang/srt/layers/attention/mamba/ops/ssd_chunk_scan.py +0 -60
- sglang/srt/layers/attention/mamba/ops/ssd_chunk_state.py +0 -111
- sglang/srt/layers/attention/mamba/ops/ssd_combined.py +0 -1
- sglang/srt/layers/attention/mamba/ops/ssd_state_passing.py +0 -11
- sglang/srt/layers/attention/npu_ops/mla_preprocess.py +1 -1
- sglang/srt/layers/attention/nsa/nsa_indexer.py +40 -83
- sglang/srt/layers/attention/nsa/triton_kernel.py +136 -0
- sglang/srt/layers/attention/nsa/utils.py +0 -1
- sglang/srt/layers/attention/nsa_backend.py +404 -90
- sglang/srt/layers/attention/triton_backend.py +208 -34
- sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py +2 -2
- sglang/srt/layers/attention/triton_ops/extend_attention.py +539 -44
- sglang/srt/layers/attention/trtllm_mha_backend.py +2 -2
- sglang/srt/layers/attention/trtllm_mla_backend.py +361 -30
- sglang/srt/layers/attention/utils.py +11 -7
- sglang/srt/layers/attention/vision.py +3 -3
- sglang/srt/layers/attention/xpu_backend.py +1028 -0
- sglang/srt/layers/communicator.py +11 -7
- sglang/srt/layers/{quantization/deep_gemm_wrapper → deep_gemm_wrapper}/compile_utils.py +4 -8
- sglang/srt/layers/{quantization/deep_gemm_wrapper → deep_gemm_wrapper}/configurer.py +4 -3
- sglang/srt/layers/{quantization/deep_gemm_wrapper → deep_gemm_wrapper}/entrypoint.py +3 -3
- sglang/srt/layers/dp_attention.py +17 -0
- sglang/srt/layers/layernorm.py +45 -15
- sglang/srt/layers/linear.py +9 -1
- sglang/srt/layers/logits_processor.py +147 -17
- sglang/srt/layers/modelopt_utils.py +11 -0
- sglang/srt/layers/moe/cutlass_moe.py +0 -2
- sglang/srt/layers/moe/cutlass_w4a8_moe.py +213 -21
- sglang/srt/layers/moe/ep_moe/kernels.py +35 -457
- sglang/srt/layers/moe/ep_moe/layer.py +119 -397
- sglang/srt/layers/moe/flashinfer_cutedsl_moe.py +1 -1
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_B200.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py +11 -3
- sglang/srt/layers/moe/fused_moe_triton/layer.py +76 -70
- sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py +18 -42
- sglang/srt/layers/moe/moe_runner/deep_gemm.py +304 -0
- sglang/srt/layers/moe/moe_runner/runner.py +3 -0
- sglang/srt/layers/moe/moe_runner/triton.py +3 -1
- sglang/srt/layers/moe/rocm_moe_utils.py +0 -1
- sglang/srt/layers/moe/router.py +51 -15
- sglang/srt/layers/moe/token_dispatcher/__init__.py +10 -0
- sglang/srt/layers/moe/token_dispatcher/base.py +1 -1
- sglang/srt/layers/moe/token_dispatcher/deepep.py +110 -97
- sglang/srt/layers/moe/token_dispatcher/mooncake.py +386 -0
- sglang/srt/layers/moe/token_dispatcher/standard.py +46 -0
- sglang/srt/layers/moe/topk.py +3 -2
- sglang/srt/layers/moe/utils.py +17 -1
- sglang/srt/layers/quantization/__init__.py +2 -53
- sglang/srt/layers/quantization/awq.py +183 -6
- sglang/srt/layers/quantization/awq_triton.py +29 -0
- sglang/srt/layers/quantization/base_config.py +20 -1
- sglang/srt/layers/quantization/compressed_tensors/__init__.py +7 -0
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py +20 -49
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +421 -70
- sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py +3 -0
- sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py +4 -22
- sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py +339 -0
- sglang/srt/layers/quantization/fp8.py +84 -18
- sglang/srt/layers/quantization/fp8_kernel.py +55 -10
- sglang/srt/layers/quantization/fp8_utils.py +42 -14
- sglang/srt/layers/quantization/fpgemm_fp8.py +2 -3
- sglang/srt/layers/quantization/gptq.py +0 -1
- sglang/srt/layers/quantization/int8_kernel.py +18 -2
- sglang/srt/layers/quantization/marlin_utils.py +12 -0
- sglang/srt/layers/quantization/modelopt_quant.py +125 -100
- sglang/srt/layers/quantization/mxfp4.py +5 -30
- sglang/srt/layers/quantization/petit.py +1 -1
- sglang/srt/layers/quantization/quark/quark.py +3 -1
- sglang/srt/layers/quantization/quark/quark_moe.py +3 -3
- sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py +0 -7
- sglang/srt/layers/quantization/unquant.py +1 -4
- sglang/srt/layers/quantization/utils.py +0 -1
- sglang/srt/layers/quantization/w4afp8.py +51 -20
- sglang/srt/layers/quantization/w8a8_int8.py +30 -24
- sglang/srt/layers/radix_attention.py +59 -9
- sglang/srt/layers/rotary_embedding.py +673 -16
- sglang/srt/layers/sampler.py +36 -16
- sglang/srt/layers/sparse_pooler.py +98 -0
- sglang/srt/layers/utils.py +0 -1
- sglang/srt/layers/vocab_parallel_embedding.py +4 -1
- sglang/srt/lora/backend/triton_backend.py +0 -1
- sglang/srt/lora/eviction_policy.py +139 -0
- sglang/srt/lora/lora_manager.py +24 -9
- sglang/srt/lora/lora_registry.py +1 -1
- sglang/srt/lora/mem_pool.py +40 -16
- sglang/srt/lora/triton_ops/chunked_sgmv_expand.py +1 -1
- sglang/srt/lora/triton_ops/chunked_sgmv_shrink.py +4 -2
- sglang/srt/managers/cache_controller.py +48 -17
- sglang/srt/managers/data_parallel_controller.py +146 -42
- sglang/srt/managers/detokenizer_manager.py +40 -13
- sglang/srt/managers/io_struct.py +66 -16
- sglang/srt/managers/mm_utils.py +20 -18
- sglang/srt/managers/multi_tokenizer_mixin.py +66 -81
- sglang/srt/managers/overlap_utils.py +96 -19
- sglang/srt/managers/schedule_batch.py +241 -511
- sglang/srt/managers/schedule_policy.py +15 -2
- sglang/srt/managers/scheduler.py +399 -499
- sglang/srt/managers/scheduler_metrics_mixin.py +55 -8
- sglang/srt/managers/scheduler_output_processor_mixin.py +317 -111
- sglang/srt/managers/scheduler_pp_mixin.py +341 -0
- sglang/srt/managers/scheduler_profiler_mixin.py +57 -10
- sglang/srt/managers/scheduler_runtime_checker_mixin.py +217 -0
- sglang/srt/managers/scheduler_update_weights_mixin.py +33 -14
- sglang/srt/managers/tokenizer_communicator_mixin.py +71 -55
- sglang/srt/managers/tokenizer_manager.py +378 -90
- sglang/srt/managers/tp_worker.py +212 -161
- sglang/srt/managers/utils.py +78 -2
- sglang/srt/mem_cache/allocator.py +7 -2
- sglang/srt/mem_cache/allocator_ascend.py +2 -2
- sglang/srt/mem_cache/base_prefix_cache.py +2 -2
- sglang/srt/mem_cache/chunk_cache.py +13 -2
- sglang/srt/mem_cache/common.py +480 -0
- sglang/srt/mem_cache/evict_policy.py +16 -1
- sglang/srt/mem_cache/hicache_storage.py +4 -1
- sglang/srt/mem_cache/hiradix_cache.py +16 -3
- sglang/srt/mem_cache/mamba_radix_cache.py +993 -0
- sglang/srt/mem_cache/memory_pool.py +435 -219
- sglang/srt/mem_cache/memory_pool_host.py +0 -1
- sglang/srt/mem_cache/multimodal_cache.py +0 -1
- sglang/srt/mem_cache/radix_cache.py +53 -19
- sglang/srt/mem_cache/radix_cache_cpp.py +19 -14
- sglang/srt/mem_cache/storage/aibrix_kvcache/aibrix_kvcache_storage.py +8 -2
- sglang/srt/mem_cache/storage/aibrix_kvcache/unit_test.py +1 -13
- sglang/srt/mem_cache/storage/backend_factory.py +2 -2
- sglang/srt/mem_cache/storage/eic/eic_storage.py +5 -6
- sglang/srt/mem_cache/storage/hf3fs/hf3fs_client.py +0 -1
- sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py +9 -3
- sglang/srt/mem_cache/storage/lmcache/lmc_radix_cache.py +5 -3
- sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py +101 -17
- sglang/srt/mem_cache/storage/nixl/hicache_nixl.py +38 -9
- sglang/srt/mem_cache/storage/nixl/nixl_utils.py +1 -1
- sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py +17 -2
- sglang/srt/mem_cache/swa_radix_cache.py +92 -26
- sglang/srt/metrics/collector.py +31 -0
- sglang/srt/metrics/func_timer.py +1 -1
- sglang/srt/model_executor/cuda_graph_runner.py +43 -5
- sglang/srt/model_executor/forward_batch_info.py +28 -23
- sglang/srt/model_executor/model_runner.py +379 -139
- sglang/srt/model_executor/npu_graph_runner.py +2 -3
- sglang/srt/model_executor/piecewise_cuda_graph_runner.py +539 -0
- sglang/srt/model_loader/__init__.py +1 -1
- sglang/srt/model_loader/loader.py +424 -27
- sglang/srt/model_loader/utils.py +0 -1
- sglang/srt/model_loader/weight_utils.py +47 -28
- sglang/srt/models/apertus.py +2 -3
- sglang/srt/models/arcee.py +2 -2
- sglang/srt/models/bailing_moe.py +13 -52
- sglang/srt/models/bailing_moe_nextn.py +3 -4
- sglang/srt/models/bert.py +1 -1
- sglang/srt/models/deepseek_nextn.py +19 -3
- sglang/srt/models/deepseek_ocr.py +1516 -0
- sglang/srt/models/deepseek_v2.py +273 -98
- sglang/srt/models/dots_ocr.py +0 -2
- sglang/srt/models/dots_vlm.py +0 -1
- sglang/srt/models/dots_vlm_vit.py +1 -1
- sglang/srt/models/falcon_h1.py +13 -19
- sglang/srt/models/gemma3_mm.py +16 -0
- sglang/srt/models/gemma3n_mm.py +1 -2
- sglang/srt/models/glm4_moe.py +14 -37
- sglang/srt/models/glm4_moe_nextn.py +2 -2
- sglang/srt/models/glm4v.py +2 -1
- sglang/srt/models/glm4v_moe.py +5 -5
- sglang/srt/models/gpt_oss.py +5 -5
- sglang/srt/models/grok.py +10 -23
- sglang/srt/models/hunyuan.py +2 -7
- sglang/srt/models/interns1.py +0 -1
- sglang/srt/models/kimi_vl.py +1 -7
- sglang/srt/models/kimi_vl_moonvit.py +3 -1
- sglang/srt/models/llama.py +2 -2
- sglang/srt/models/llama_eagle3.py +1 -1
- sglang/srt/models/longcat_flash.py +5 -22
- sglang/srt/models/longcat_flash_nextn.py +3 -14
- sglang/srt/models/mimo.py +2 -13
- sglang/srt/models/mimo_mtp.py +1 -2
- sglang/srt/models/minicpmo.py +7 -5
- sglang/srt/models/mixtral.py +1 -4
- sglang/srt/models/mllama.py +1 -1
- sglang/srt/models/mllama4.py +13 -3
- sglang/srt/models/nemotron_h.py +511 -0
- sglang/srt/models/olmo2.py +31 -4
- sglang/srt/models/opt.py +5 -5
- sglang/srt/models/phi.py +1 -1
- sglang/srt/models/phi4mm.py +1 -1
- sglang/srt/models/phimoe.py +0 -1
- sglang/srt/models/pixtral.py +0 -3
- sglang/srt/models/points_v15_chat.py +186 -0
- sglang/srt/models/qwen.py +0 -1
- sglang/srt/models/qwen2_5_vl.py +3 -3
- sglang/srt/models/qwen2_audio.py +2 -15
- sglang/srt/models/qwen2_moe.py +15 -12
- sglang/srt/models/qwen2_vl.py +5 -2
- sglang/srt/models/qwen3_moe.py +19 -35
- sglang/srt/models/qwen3_next.py +7 -12
- sglang/srt/models/qwen3_next_mtp.py +3 -4
- sglang/srt/models/qwen3_omni_moe.py +661 -0
- sglang/srt/models/qwen3_vl.py +37 -33
- sglang/srt/models/qwen3_vl_moe.py +57 -185
- sglang/srt/models/roberta.py +55 -3
- sglang/srt/models/sarashina2_vision.py +0 -1
- sglang/srt/models/step3_vl.py +3 -5
- sglang/srt/models/utils.py +11 -1
- sglang/srt/multimodal/processors/base_processor.py +6 -2
- sglang/srt/multimodal/processors/deepseek_ocr.py +37 -0
- sglang/srt/multimodal/processors/deepseek_vl_v2.py +0 -3
- sglang/srt/multimodal/processors/dots_vlm.py +0 -1
- sglang/srt/multimodal/processors/glm4v.py +1 -5
- sglang/srt/multimodal/processors/internvl.py +0 -2
- sglang/srt/multimodal/processors/janus_pro.py +0 -1
- sglang/srt/multimodal/processors/mllama4.py +0 -8
- sglang/srt/multimodal/processors/phi4mm.py +0 -1
- sglang/srt/multimodal/processors/points_v15_chat.py +52 -0
- sglang/srt/multimodal/processors/qwen_vl.py +75 -16
- sglang/srt/multimodal/processors/step3_vl.py +1 -1
- sglang/srt/parser/conversation.py +41 -0
- sglang/srt/parser/reasoning_parser.py +0 -1
- sglang/srt/sampling/custom_logit_processor.py +77 -2
- sglang/srt/sampling/sampling_batch_info.py +17 -22
- sglang/srt/sampling/sampling_params.py +70 -2
- sglang/srt/server_args.py +577 -73
- sglang/srt/server_args_config_parser.py +1 -1
- sglang/srt/single_batch_overlap.py +38 -28
- sglang/srt/speculative/base_spec_worker.py +34 -0
- sglang/srt/speculative/draft_utils.py +226 -0
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +24 -7
- sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py +23 -2
- sglang/srt/speculative/eagle_info.py +57 -18
- sglang/srt/speculative/eagle_info_v2.py +458 -0
- sglang/srt/speculative/eagle_utils.py +138 -0
- sglang/srt/speculative/eagle_worker.py +83 -280
- sglang/srt/speculative/eagle_worker_v2.py +702 -0
- sglang/srt/speculative/{ngram_utils.py → ngram_info.py} +14 -9
- sglang/srt/speculative/ngram_worker.py +12 -11
- sglang/srt/speculative/spec_info.py +2 -0
- sglang/srt/speculative/spec_utils.py +38 -3
- sglang/srt/speculative/standalone_worker.py +4 -14
- sglang/srt/tokenizer/tiktoken_tokenizer.py +2 -2
- sglang/srt/two_batch_overlap.py +28 -14
- sglang/srt/utils/__init__.py +1 -1
- sglang/srt/{bench_utils.py → utils/bench_utils.py} +4 -2
- sglang/srt/utils/common.py +192 -47
- sglang/srt/utils/hf_transformers_utils.py +40 -17
- sglang/srt/{host_shared_memory.py → utils/host_shared_memory.py} +0 -1
- sglang/srt/{offloader.py → utils/offloader.py} +4 -4
- sglang/srt/utils/profile_merger.py +199 -0
- sglang/test/attention/test_flashattn_backend.py +1 -1
- sglang/test/attention/test_flashattn_mla_backend.py +0 -1
- sglang/test/attention/test_prefix_chunk_info.py +0 -2
- sglang/test/attention/test_trtllm_mla_backend.py +221 -53
- sglang/test/few_shot_gsm8k_engine.py +2 -4
- sglang/test/kit_matched_stop.py +157 -0
- sglang/test/longbench_v2/__init__.py +1 -0
- sglang/test/longbench_v2/test_longbench_v2_eval.py +238 -0
- sglang/test/longbench_v2/validate_longbench_v2.py +337 -0
- sglang/test/longbench_v2/validate_longbench_v2_standalone.py +306 -0
- sglang/test/run_eval.py +41 -0
- sglang/test/runners.py +2 -0
- sglang/test/send_one.py +42 -7
- sglang/test/simple_eval_common.py +3 -0
- sglang/test/simple_eval_gpqa.py +0 -1
- sglang/test/simple_eval_humaneval.py +0 -3
- sglang/test/simple_eval_longbench_v2.py +344 -0
- sglang/test/test_block_fp8.py +1 -2
- sglang/test/test_block_fp8_deep_gemm_blackwell.py +0 -1
- sglang/test/test_cutlass_moe.py +1 -2
- sglang/test/test_cutlass_w4a8_moe.py +10 -20
- sglang/test/test_deterministic.py +232 -99
- sglang/test/test_deterministic_utils.py +73 -0
- sglang/test/test_disaggregation_utils.py +81 -0
- sglang/test/test_marlin_moe.py +0 -1
- sglang/test/test_utils.py +85 -20
- sglang/version.py +1 -1
- {sglang-0.5.3rc2.dist-info → sglang-0.5.4.dist-info}/METADATA +45 -33
- {sglang-0.5.3rc2.dist-info → sglang-0.5.4.dist-info}/RECORD +404 -345
- sglang/srt/layers/attention/mamba/mamba_utils.py +0 -81
- sglang/srt/managers/tp_worker_overlap_thread.py +0 -311
- sglang/srt/speculative/build_eagle_tree.py +0 -427
- sglang/test/test_block_fp8_ep.py +0 -358
- /sglang/srt/layers/{quantization/deep_gemm_wrapper → deep_gemm_wrapper}/__init__.py +0 -0
- /sglang/srt/{aio_rwlock.py → utils/aio_rwlock.py} +0 -0
- /sglang/srt/{torch_memory_saver_adapter.py → utils/torch_memory_saver_adapter.py} +0 -0
- {sglang-0.5.3rc2.dist-info → sglang-0.5.4.dist-info}/WHEEL +0 -0
- {sglang-0.5.3rc2.dist-info → sglang-0.5.4.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.5.3rc2.dist-info → sglang-0.5.4.dist-info}/top_level.txt +0 -0
|
@@ -1,23 +1,23 @@
|
|
|
1
1
|
sglang/__init__.py,sha256=CK60u1J439CJZaPihWqlDjFZ8doIC-5YgIYz-E1PIh4,1823
|
|
2
2
|
sglang/bench_offline_throughput.py,sha256=Bge0KG4Uiv9CHsxDnqKdXJmG_TcxM4blz3CmvLmDRvM,14815
|
|
3
|
-
sglang/bench_one_batch.py,sha256=
|
|
4
|
-
sglang/bench_one_batch_server.py,sha256=
|
|
5
|
-
sglang/bench_serving.py,sha256=
|
|
6
|
-
sglang/check_env.py,sha256=
|
|
7
|
-
sglang/compile_deep_gemm.py,sha256=
|
|
8
|
-
sglang/global_config.py,sha256=
|
|
9
|
-
sglang/launch_server.py,sha256=
|
|
10
|
-
sglang/profiler.py,sha256=
|
|
3
|
+
sglang/bench_one_batch.py,sha256=cjECJgTmPcnP-b8Fcy7ldFU6FaEqBpz7Z45RTwBwNR8,23763
|
|
4
|
+
sglang/bench_one_batch_server.py,sha256=8zAjLFu0tgfIhhtEaPGdDhi15YCcHcaK19vz6Rmn_Jw,26565
|
|
5
|
+
sglang/bench_serving.py,sha256=KrPHSzFmzyhRerLBBOm-72sOr1toBQkNIOvRPdVBBc0,94023
|
|
6
|
+
sglang/check_env.py,sha256=6wRlWL7UwY1JjYRG307bLLJRoirPk2RVLYrDWV8Et0c,8413
|
|
7
|
+
sglang/compile_deep_gemm.py,sha256=v7WJZLSrJw3Vc_28lTReRDJ1WdiPKLRHizFi2l2chv8,6614
|
|
8
|
+
sglang/global_config.py,sha256=bVpUL_gMSA0FwJl8y8tP5CIa7d083o6Dcak-yRytzGw,767
|
|
9
|
+
sglang/launch_server.py,sha256=VqPi2ecJmQuvw1aYppiKEp45NC_FthgBjzhHM2pXItY,620
|
|
10
|
+
sglang/profiler.py,sha256=uprc8Lo-WeqrQY9u2Wj503swEp4P_2laLJ6cWGALgME,4854
|
|
11
11
|
sglang/utils.py,sha256=YreOyt4-fWdDcg01abaMJ0y0ly4gYps26vRlmWhwGC8,17267
|
|
12
|
-
sglang/version.py,sha256=
|
|
12
|
+
sglang/version.py,sha256=DITpct-LrdIsTgwx2NgH5Ghx5y8Xgz1YMimy1ZV5RTY,22
|
|
13
13
|
sglang/eval/llama3_eval.py,sha256=mLNRZJIqV4CfqrY8UGnJEcHw2Xsyr1eyYZgFSUFYr1g,9997
|
|
14
14
|
sglang/eval/loogle_eval.py,sha256=-CC2s2kh5qUoDrHRkQVkC_jNvBgNojXbf456ny5s78s,4557
|
|
15
|
-
sglang/lang/api.py,sha256=
|
|
15
|
+
sglang/lang/api.py,sha256=kyfJuErqMyle6hnx3Q_oqNSFDe0q4gFob1yd5ZLTatw,7438
|
|
16
16
|
sglang/lang/chat_template.py,sha256=4_JVa7NDpHP2it6rAQS5UnCSxSMy0rtfdOgSvH_Kbdc,22549
|
|
17
17
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
|
18
18
|
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
|
19
|
-
sglang/lang/interpreter.py,sha256=
|
|
20
|
-
sglang/lang/ir.py,sha256=
|
|
19
|
+
sglang/lang/interpreter.py,sha256=wy6dWNzk57Mp7U15I3VeCT_UFBSnLmff2vXRdDbh1hE,34844
|
|
20
|
+
sglang/lang/ir.py,sha256=wcV1dMwn-L6gK-ERu-Gg_2dqCkAuWkFNIGh0kRhFa7M,20184
|
|
21
21
|
sglang/lang/tracer.py,sha256=ljBo9VZ0zVaGwzNk32qw21acyo60N0UjIjqBbT5a1WI,8175
|
|
22
22
|
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
|
23
23
|
sglang/lang/backend/base_backend.py,sha256=tEutGCU5tni1xGlrIjAVvA9aflJBt2duKrIDzqabJWc,1975
|
|
@@ -25,148 +25,167 @@ sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThc
|
|
|
25
25
|
sglang/lang/backend/openai.py,sha256=YFs7pCDK6_DoYmjTa-vgDVdaeE4PYr7E-sIC1q7vAns,16422
|
|
26
26
|
sglang/lang/backend/runtime_endpoint.py,sha256=UZRKqQ8eE_N11oiv9rViF3THNq21A_uio0N0Bt9MaY8,17487
|
|
27
27
|
sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZpI,4827
|
|
28
|
-
sglang/srt/_custom_ops.py,sha256=
|
|
29
|
-
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
|
30
|
-
sglang/srt/bench_utils.py,sha256=zNTsTBUta27XxojgvR5p5X9M0v1MFzZ7dcX9TMq4NvQ,4348
|
|
28
|
+
sglang/srt/_custom_ops.py,sha256=P4MLtuF8DzK66R_Sw88AYsiCOn7YNGZ93H7isJq0dUA,5356
|
|
31
29
|
sglang/srt/constants.py,sha256=0i-tEwG2BSYNDy96MxnGHV5HnBELkYcnsVGsE-R18o0,93
|
|
32
30
|
sglang/srt/custom_op.py,sha256=m5F7x3LHlnOuesmcNmJtIWsfHGFLBJ807vKc05Gu1D0,3312
|
|
33
|
-
sglang/srt/environ.py,sha256=
|
|
34
|
-
sglang/srt/host_shared_memory.py,sha256=00TgVm3PNCl4rTPJZChG5uu4I5hd_Xf587r39tibmIg,2274
|
|
35
|
-
sglang/srt/offloader.py,sha256=cYON5jZErAp88Sh5JseaRw0B2Ho2MQz9smgvrTc-2KA,18765
|
|
31
|
+
sglang/srt/environ.py,sha256=2D5x1OaR_lRd-oSLilf1lZo01Pqz2_t5Bru-LHIxYys,10447
|
|
36
32
|
sglang/srt/operations.py,sha256=za_h1_kcR1Te6-i_r0i_zAeumbmIRhLK2pS31sukkrw,6089
|
|
37
33
|
sglang/srt/operations_strategy.py,sha256=-w6GI2VgSGvORy3pUWRAJo6244ykSW1ZBV1Dx0fZlHA,7138
|
|
38
|
-
sglang/srt/server_args.py,sha256=
|
|
39
|
-
sglang/srt/server_args_config_parser.py,sha256=
|
|
40
|
-
sglang/srt/single_batch_overlap.py,sha256=
|
|
41
|
-
sglang/srt/
|
|
42
|
-
sglang/srt/two_batch_overlap.py,sha256=0cHUV2ZeyCaojDRpqNcRSUIQM3_Y4H4HfssML2gt_6k,34240
|
|
34
|
+
sglang/srt/server_args.py,sha256=Qen-c7jcgQpTrub1ogsyxX_8Joj7WfP_rA6ZMIfsH-Q,160382
|
|
35
|
+
sglang/srt/server_args_config_parser.py,sha256=NW_tnD_ixnIpEhIuhn1W67pnAOJSGWKKN-jHcssKD-Q,5213
|
|
36
|
+
sglang/srt/single_batch_overlap.py,sha256=mUW2yBRxLWKlDlpTqIKkICWzMkcbKsmPjUtcvGiVYq4,5388
|
|
37
|
+
sglang/srt/two_batch_overlap.py,sha256=xDDMyE1hKQPq-yu_GkVnNXskyc1CVoPYPaB6AvoPXKA,34667
|
|
43
38
|
sglang/srt/warmup.py,sha256=fQYzNp-I9mZccs2BerI6mOZd1CDQjdiuFCeUkcwiOb4,1834
|
|
44
39
|
sglang/srt/batch_invariant_ops/__init__.py,sha256=Z9TvOE4BL7cAaBIePEsVglH7RcWBSBIsSHs-XbveQNE,728
|
|
45
|
-
sglang/srt/batch_invariant_ops/batch_invariant_ops.py,sha256=
|
|
46
|
-
sglang/srt/
|
|
40
|
+
sglang/srt/batch_invariant_ops/batch_invariant_ops.py,sha256=Kb4uxHPDwlQYg1CfEOhuRDcHTI3Yr8Kbq3GkF57iUZs,16249
|
|
41
|
+
sglang/srt/checkpoint_engine/checkpoint_engine_worker.py,sha256=YlyiZ46LOi5aib0N5IyrPMuGbnVi_Xnnf9r2XdR1OtY,5509
|
|
42
|
+
sglang/srt/compilation/backend.py,sha256=SClr9jjC8wb8vymB2cE-6DN36bEbZeBlYcFx0qe-pfM,14395
|
|
43
|
+
sglang/srt/compilation/compilation_config.py,sha256=9GDBY3SAV5hIJ6hmYurJ3vfYh9-gtZP3nEzp0TrUdeM,617
|
|
44
|
+
sglang/srt/compilation/compilation_counter.py,sha256=qrCqMCaui2eOBpxi3ZBiuvmJ6dkWah_6dYjhvu6_MqE,1623
|
|
45
|
+
sglang/srt/compilation/compile.py,sha256=All4G5VjYBY9MOalW5YDo17eEtho-o_BG5V86lNJ-5c,6965
|
|
46
|
+
sglang/srt/compilation/compiler_interface.py,sha256=k6EDIpdtEB0NCOaDxsgXwaSXH4xTLQsflFdy-sTsyRQ,19508
|
|
47
|
+
sglang/srt/compilation/cuda_piecewise_backend.py,sha256=_MOgUhUGg9kBDIhSJWq-vUwZrluwScy4PbCzD-X9g7g,9237
|
|
48
|
+
sglang/srt/compilation/fix_functionalization.py,sha256=SDQ1Pbvh5PiUg3M82NAfyXPjz21wmBRQgzM_HHKRHss,5156
|
|
49
|
+
sglang/srt/compilation/fx_utils.py,sha256=vv32jqNIYcdvLiz0W4yGcUyh_ko6LJwrES8ZMU2vIis,2873
|
|
50
|
+
sglang/srt/compilation/inductor_pass.py,sha256=zebqIifs0wvLXIUy43ablX87qh4jnn9876ZHzw4c2IQ,4041
|
|
51
|
+
sglang/srt/compilation/pass_manager.py,sha256=n8TIJkWIxegDd5lX6Xja4l4YuBQLZvn2_9yEY8Esp80,2213
|
|
52
|
+
sglang/srt/compilation/piecewise_context_manager.py,sha256=P-WpB3Ny8sMEFUpkQv4ExSoqQPPyEwhXZraDWQjP8ak,1113
|
|
53
|
+
sglang/srt/compilation/weak_ref_tensor_jit.py,sha256=XJLJsj5t84QLhF0Bjx0j2Iow51d8zc6inASOd9watFA,390
|
|
54
|
+
sglang/srt/configs/__init__.py,sha256=a8_ODqcCzMN1q_fNHKMBNHM9aGH8LF92GLGcLeViLWY,1291
|
|
47
55
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
|
48
56
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
|
49
|
-
sglang/srt/configs/
|
|
57
|
+
sglang/srt/configs/deepseek_ocr.py,sha256=3nZL7pWJ-WwN6ZYqRsPy7zbxgZCggW5igVfIvJhGUXY,8102
|
|
58
|
+
sglang/srt/configs/deepseekvl2.py,sha256=QTZnL47wIx0mkd_HCn_Kfzu4oCHEJaYZpvVSjmaDvp8,26518
|
|
50
59
|
sglang/srt/configs/device_config.py,sha256=1Iaxrk65bJsCWV3E2cDfiap_T_xJIIj9oFVn9y6v0EI,515
|
|
51
60
|
sglang/srt/configs/dots_ocr.py,sha256=HSKerqzHzrKIzoNZOUXA_KiBLmL-Rs8h4Vw17pjF1Uo,1863
|
|
52
|
-
sglang/srt/configs/dots_vlm.py,sha256=
|
|
61
|
+
sglang/srt/configs/dots_vlm.py,sha256=Q2qaP65sYCKGmg_bvc4g5yb-pasdZNx4xnnlzu6Ed1U,4912
|
|
53
62
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
|
54
|
-
sglang/srt/configs/falcon_h1.py,sha256=
|
|
63
|
+
sglang/srt/configs/falcon_h1.py,sha256=LFxN0We8Gfgk-RWVeegzvyh-R4msAYF96ioO97Ta4ig,14939
|
|
55
64
|
sglang/srt/configs/internvl.py,sha256=rIC-CBWJHy-Mjmk0_H3YcvVmZzeCRbXGo3dQMex-yeg,28141
|
|
56
65
|
sglang/srt/configs/janus_pro.py,sha256=yI2c_aWBIKiTcK6RZxK6hq8CIxyYRH_NN8uaSNKsrKI,19156
|
|
57
66
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
|
58
67
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
|
59
|
-
sglang/srt/configs/load_config.py,sha256=
|
|
68
|
+
sglang/srt/configs/load_config.py,sha256=_x9n6Rkbi3VqYmXJ7PNdce32mvUNP1ewqrkUsJ7qprw,4765
|
|
60
69
|
sglang/srt/configs/longcat_flash.py,sha256=Qp25xJVLq2K72Z80cXhcJxtqhagAdiPySDoevuT0Sno,3589
|
|
61
|
-
sglang/srt/configs/
|
|
62
|
-
sglang/srt/configs/
|
|
63
|
-
sglang/srt/configs/
|
|
70
|
+
sglang/srt/configs/mamba_utils.py,sha256=AD96wj8FCxRsEovdtGn88xzcKAw5KErbO5xFSk0xwxc,3684
|
|
71
|
+
sglang/srt/configs/model_config.py,sha256=7KAlFFRQr9Vsj2PzFBsGnmzXQGWo3eHtftSnaQjDruE,39695
|
|
72
|
+
sglang/srt/configs/modelopt_config.py,sha256=pr4Q_J4G1Ff-wy24BYRzWaN0UI34rreGef7Nt6d0X3M,1070
|
|
73
|
+
sglang/srt/configs/nemotron_h.py,sha256=X39hWm2KQoAcZ4HXKDCfbua9aOTlcxcK89c52cmAq-k,13072
|
|
74
|
+
sglang/srt/configs/olmo3.py,sha256=DOyp1cNi_n8ckz9Ohs3zUZqkk6n26UBsNQ3zngHNNNY,3600
|
|
75
|
+
sglang/srt/configs/points_v15_chat.py,sha256=qand7WMc3L96wg-wzA9YqnzMz7ZUM6quAuThjO1rfM8,983
|
|
76
|
+
sglang/srt/configs/qwen3_next.py,sha256=XQje5KTnw2aA187DNkAFRUbIPFnTsKwl64FJCW1gcLA,14884
|
|
77
|
+
sglang/srt/configs/qwen3_omni.py,sha256=m6NxdP-iKVkKuYARukqjNhQ01D5gmNQOsfFKU5qZEqI,22384
|
|
78
|
+
sglang/srt/configs/qwen3_vl.py,sha256=0Coyj3ZYUJIgEfxt_6xx8wgd5Fy1tkMAeEhIaXXaZyk,28854
|
|
64
79
|
sglang/srt/configs/step3_vl.py,sha256=_Otgnym57DVgB_kZ__8c1_Ys5gSalA_K0ZuVjcG51T0,4845
|
|
65
80
|
sglang/srt/configs/update_config.py,sha256=GEf-XhL8JPrbX9-Hz8V7S3M6YTg76DVdIhc_4YdMDtc,6291
|
|
66
81
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
|
67
82
|
sglang/srt/connector/__init__.py,sha256=zPuaRKulJsrDyT3OtN9wUT-4fqQBX-cJr2fZUB0_KPM,1562
|
|
68
83
|
sglang/srt/connector/base_connector.py,sha256=LCKsTX_yWHclPrzNNB1fLwVCN8rIDKZaZhqHQ54B9MU,2774
|
|
69
84
|
sglang/srt/connector/redis.py,sha256=K3fJSm2rZsd0R_KkICV3jIWKtrwxXE1tYktWnovLbz4,2514
|
|
70
|
-
sglang/srt/connector/remote_instance.py,sha256=
|
|
85
|
+
sglang/srt/connector/remote_instance.py,sha256=LpPVftvXN0xRVPthwFm2fgnuvxSlYxwE_47NRGAmkmY,2704
|
|
71
86
|
sglang/srt/connector/s3.py,sha256=hn5Ow9Y6ItS8RMJDwnTQe5QaiQ7HKMgiwggE9QnUewM,3743
|
|
72
87
|
sglang/srt/connector/utils.py,sha256=isTvxauz1_8no5MW6p8Bwj2H9mQkweaRO_RSwAPA7R8,983
|
|
73
88
|
sglang/srt/connector/serde/__init__.py,sha256=zuleyYN-jrDyiPiXjTbQKA27llb4H7HuDTZcBwrLk1U,707
|
|
74
89
|
sglang/srt/connector/serde/safe_serde.py,sha256=XSjb9mRv1HqeG6Jiw633EOQYlrcI23Q21UluYqPZaWA,760
|
|
75
90
|
sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOUIhF0ZA,1004
|
|
76
|
-
sglang/srt/constrained/base_grammar_backend.py,sha256=
|
|
77
|
-
sglang/srt/constrained/llguidance_backend.py,sha256=
|
|
78
|
-
sglang/srt/constrained/outlines_backend.py,sha256=
|
|
91
|
+
sglang/srt/constrained/base_grammar_backend.py,sha256=LVEaY4JrF8zCbn1chwva0zJ9cW00dZ4yVTREmzJx9Zs,8307
|
|
92
|
+
sglang/srt/constrained/llguidance_backend.py,sha256=OxJoMbhi1InKzxMkGQrvetWU5GR9n8C1jc74fHBFQtc,6433
|
|
93
|
+
sglang/srt/constrained/outlines_backend.py,sha256=1pQNeROdrFBiXIIkIYKB0xufIfp6KDxm8G7C_xMooH8,6889
|
|
79
94
|
sglang/srt/constrained/outlines_jump_forward.py,sha256=dm3PVswx2oE_JfAv-tPd7irMI95VCq4cZT-AF-Ohx3s,6823
|
|
80
|
-
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=
|
|
81
|
-
sglang/srt/constrained/
|
|
95
|
+
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=O36HzXEB-YKgo0recrLtW36EiTZIBbpnbHBPeGkWEyI,3334
|
|
96
|
+
sglang/srt/constrained/utils.py,sha256=ZDXuyKjGYHfPo3ZhcgxZe7pk_Qb4_ilBV2WjbDRXKDc,418
|
|
97
|
+
sglang/srt/constrained/xgrammar_backend.py,sha256=x7iwMMojTI3pcMmnyUPI1k4bCRoe1IIw76_IIJTAXBs,9855
|
|
82
98
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
|
83
99
|
sglang/srt/debug_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
84
100
|
sglang/srt/debug_utils/dump_comparator.py,sha256=3rWdv4BQXTDtB3z5ao9VPN5lK31ImKf2zMWX7f0Xe6s,5394
|
|
85
101
|
sglang/srt/debug_utils/dump_loader.py,sha256=RzWpl7RsDRw98DJMEvf6U9c9fPiobyeWI8opmRaRGGA,2632
|
|
86
102
|
sglang/srt/debug_utils/dumper.py,sha256=6frfI4WErneQE4RpXgAR5gZJQRdzcQjyO3McW56jgYo,3517
|
|
87
103
|
sglang/srt/debug_utils/text_comparator.py,sha256=NLJdjUikW--bWnGQWIeFJesyuvZ2Vni2S53fIED-m8s,7370
|
|
88
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
|
89
|
-
sglang/srt/disaggregation/decode_kvcache_offload_manager.py,sha256=
|
|
104
|
+
sglang/srt/disaggregation/decode.py,sha256=EJNSz7J2hmO5VuqXu14O6k57w7WizFRK5n1uE8iSzdY,40441
|
|
105
|
+
sglang/srt/disaggregation/decode_kvcache_offload_manager.py,sha256=jD_O-uRaZ5cD8C9qtto6m5ZXyM86loJzkdLgwheMBao,7045
|
|
90
106
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=BeGxXbFLW_ZbuyOs0idWzlicCh6NA1pTOXgON5SAdaE,6947
|
|
91
107
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
|
92
108
|
sglang/srt/disaggregation/mini_lb.py,sha256=JY2uCeUM3Zk3FdGWmCQBY3LeiJ5FM1PlrqAW8wJTTHI,395
|
|
93
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
|
109
|
+
sglang/srt/disaggregation/prefill.py,sha256=crU3CZ5oITm3W9dSxIsvbPIwzOM9dPDOhPTELZcYepA,28325
|
|
94
110
|
sglang/srt/disaggregation/utils.py,sha256=oBMqYOMAnyK4T69fFaDIuM1AAGa2vOvoA-CBtGocOkk,12263
|
|
95
111
|
sglang/srt/disaggregation/ascend/__init__.py,sha256=-lxnica6fZYmYNpKwmE8yESUpQ5Sxf2DiZoBHzboKc8,146
|
|
96
112
|
sglang/srt/disaggregation/ascend/conn.py,sha256=Z0xTJjSYXal7uGA5e7ci4oxOcWdC9qrV-gMd06ikp2w,4109
|
|
97
|
-
sglang/srt/disaggregation/ascend/transfer_engine.py,sha256=
|
|
113
|
+
sglang/srt/disaggregation/ascend/transfer_engine.py,sha256=MK9G22_YUkvpaH4XVvKe1iz7F-bzhOdtYaVQ2jKiY2s,3567
|
|
98
114
|
sglang/srt/disaggregation/base/__init__.py,sha256=4VwUv0aWxwmVL1049XK82aLTNxmt0WY5RPy9li-wyVk,160
|
|
99
|
-
sglang/srt/disaggregation/base/conn.py,sha256=
|
|
115
|
+
sglang/srt/disaggregation/base/conn.py,sha256=SvNYNFIjC0adxt0vs3g80P-vdVCleBPE4VKs0-hUIz4,3271
|
|
100
116
|
sglang/srt/disaggregation/common/__init__.py,sha256=7yl-EGLMVKRpBUaGF_7lwAsw2J_mqpRZV0238VGxD9o,126
|
|
101
|
-
sglang/srt/disaggregation/common/conn.py,sha256=
|
|
117
|
+
sglang/srt/disaggregation/common/conn.py,sha256=mlZJnlsvdS2WxapGtMhV1YpE9M9zLm2NXPMNuI7PSFo,24443
|
|
102
118
|
sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeKVPMWPcB5ywbE,1194
|
|
103
119
|
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
|
104
|
-
sglang/srt/disaggregation/fake/conn.py,sha256=
|
|
120
|
+
sglang/srt/disaggregation/fake/conn.py,sha256=C5gYCsqf-CfffDhqzbp4FL1GQ3xFo_OvKkcC4W6R1OM,2502
|
|
105
121
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
|
106
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
|
122
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=ruE4Rb0dPIhAmpQEKkePgnyRDG0xMbySgsrCb7wFIh8,56422
|
|
107
123
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=O-XRmQ3QwD6RuiyRgw4ZohSrFkuPdppV_eDBMUXn0jk,5884
|
|
108
124
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
|
109
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
|
125
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=w_kDDEB4fIvDe-Z7ufxmw_cpDR57xXJVQrqWvYe88vo,33788
|
|
110
126
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
|
111
127
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
|
112
|
-
sglang/srt/distributed/naive_distributed.py,sha256=
|
|
113
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
|
128
|
+
sglang/srt/distributed/naive_distributed.py,sha256=GX7CHhUb9rIQuaIPX4TYm01S7XQdBXvdqaJoPdxFyAI,3317
|
|
129
|
+
sglang/srt/distributed/parallel_state.py,sha256=SHisHdAql3dVBFUR1zIZo3apQMejRPh0hQYn5AaA9N8,70931
|
|
114
130
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
|
115
|
-
sglang/srt/distributed/device_communicators/all_reduce_utils.py,sha256=
|
|
131
|
+
sglang/srt/distributed/device_communicators/all_reduce_utils.py,sha256=dk-uFaKZgVG-1dZDwMT6GvpFi2xP0DJRJ9BiRjHq0zw,336
|
|
116
132
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
|
117
|
-
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=
|
|
133
|
+
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=RCF9FzJYI9EzlNEDUZB-uL_0VKjTqNn0_MfZED-0RhA,16615
|
|
118
134
|
sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py,sha256=Fx9D70NO2dplyuqOxTasMwkzONN3wfC4WOny3tWSbPA,14159
|
|
119
135
|
sglang/srt/distributed/device_communicators/hpu_communicator.py,sha256=gPjEH1-izoby5uDrfUlzNf21luPT0Ow7pJjhCRKnHy8,1728
|
|
120
136
|
sglang/srt/distributed/device_communicators/npu_communicator.py,sha256=bRXN1Md_4SHQGzQYZa2GrHv2zbIU5vSpkueHiAZL1xQ,1345
|
|
121
|
-
sglang/srt/distributed/device_communicators/pymscclpp.py,sha256=
|
|
122
|
-
sglang/srt/distributed/device_communicators/pynccl.py,sha256=
|
|
123
|
-
sglang/srt/distributed/device_communicators/pynccl_allocator.py,sha256=
|
|
137
|
+
sglang/srt/distributed/device_communicators/pymscclpp.py,sha256=8ujiWibMH36TGh0kWnJKcP_AqaVAX0dYhJHtZemRefM,10874
|
|
138
|
+
sglang/srt/distributed/device_communicators/pynccl.py,sha256=TqczleI5orlLfP3UkhccOIQexh_ih1b98kqUxtE42jY,12813
|
|
139
|
+
sglang/srt/distributed/device_communicators/pynccl_allocator.py,sha256=jNvIJiYPiEJYV6Q0kvcdbYZfxjh7wq0yWiRJuWWzYi8,4756
|
|
124
140
|
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=BLGEl90GZSl3K-04x7eCTaVmpZBXpcb7uJakAseteFU,18539
|
|
125
141
|
sglang/srt/distributed/device_communicators/quick_all_reduce.py,sha256=4j1_E4azoxfd8wxtfFmt9rvbQncl8ny6wmTMl6gAkp0,9932
|
|
126
142
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=q68niUgh8zF7CgNwqny9vaZU1aHGpLSrxBMiUWZ5Nsk,20969
|
|
127
|
-
sglang/srt/distributed/device_communicators/symm_mem.py,sha256=
|
|
143
|
+
sglang/srt/distributed/device_communicators/symm_mem.py,sha256=MauP4LGMIKSfoDx-L8o0kaXg7rsAuVDT92ugjlM68xM,5641
|
|
128
144
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
|
145
|
+
sglang/srt/elastic_ep/elastic_ep.py,sha256=KaSUAi0JHB82desvcv-TW5_PYCrzQStslOCcl9_g-LM,2311
|
|
129
146
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
|
130
|
-
sglang/srt/entrypoints/context.py,sha256=
|
|
131
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
|
132
|
-
sglang/srt/entrypoints/
|
|
133
|
-
sglang/srt/entrypoints/
|
|
134
|
-
sglang/srt/entrypoints/
|
|
135
|
-
sglang/srt/entrypoints/
|
|
136
|
-
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
|
147
|
+
sglang/srt/entrypoints/context.py,sha256=YQdVLmELQD1tNT6Q1BLl04sATwTJAAomCATZyD19S8g,8035
|
|
148
|
+
sglang/srt/entrypoints/engine.py,sha256=yiIVBjbMLgL1s5A19bShgeqRdAQlv3OGfz5swHNTunc,35010
|
|
149
|
+
sglang/srt/entrypoints/grpc_server.py,sha256=CHiZDErgPHnVp8PtfH246U6Eq_BEoKANJKAttNYXjBQ,38869
|
|
150
|
+
sglang/srt/entrypoints/harmony_utils.py,sha256=FhpPFnwgy1-qLnu_HZAk5V_RPmQkT81dFVp8A6xINEU,13594
|
|
151
|
+
sglang/srt/entrypoints/http_server.py,sha256=Y1Rl71phsasv8Tot1wlKl1GpJK2b_xqT_EqPEfjKOTM,56378
|
|
152
|
+
sglang/srt/entrypoints/http_server_engine.py,sha256=rWgdCYLZZP89MA-Y-hfACQqdDu0LC7lLYghi2wk-nU8,4809
|
|
137
153
|
sglang/srt/entrypoints/tool.py,sha256=aAXEjBqkr5j6_IgRL8fZCKgoDPY2TikM20-LQXU9TaI,2709
|
|
138
154
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
139
|
-
sglang/srt/entrypoints/openai/protocol.py,sha256=
|
|
140
|
-
sglang/srt/entrypoints/openai/serving_base.py,sha256
|
|
141
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
|
142
|
-
sglang/srt/entrypoints/openai/
|
|
155
|
+
sglang/srt/entrypoints/openai/protocol.py,sha256=NkK_i-Njzxzp_FIVFoOJXonz0kdYLtf_crLBuj69LoI,39612
|
|
156
|
+
sglang/srt/entrypoints/openai/serving_base.py,sha256=-L4lcJCTCJPEmtYHtQXLFgJnvJ3CbUp80uyEI0X_C6w,9665
|
|
157
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=NQs4XRPE7JEV8Mmpe1XSVWKD4VQxr8Fcw1ItLUeO3jA,47908
|
|
158
|
+
sglang/srt/entrypoints/openai/serving_classify.py,sha256=ifEjD-2rq7izbgITMB_nZkrUDN8wj73ZMV634G_HJ4U,7148
|
|
159
|
+
sglang/srt/entrypoints/openai/serving_completions.py,sha256=-kTg3BYaKLmnneKh-1_2QVC0KPg1e2VV1DEKImG9KpM,18831
|
|
143
160
|
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=H7Nv1vSUuyOUXBeaNvYB4XMFxmcJc8or7MUKyuAw_XA,6435
|
|
144
161
|
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=G79XdomjzLhH1YCbGR4alSxWO9NNmi7U-YSPsH61cjk,3379
|
|
145
|
-
sglang/srt/entrypoints/openai/serving_responses.py,sha256=
|
|
162
|
+
sglang/srt/entrypoints/openai/serving_responses.py,sha256=LDnLzUHpNrIibmUWlqCAtosUg7X3G-AIOvnUJ6etDwg,55122
|
|
146
163
|
sglang/srt/entrypoints/openai/serving_score.py,sha256=LuwXzWRAMm-xMK8ZjP3JaJ84Gxjr0Oi-e3keCsIgK38,1992
|
|
164
|
+
sglang/srt/entrypoints/openai/serving_tokenize.py,sha256=kgLBC8a_j16T2Gm5nv4DaUjjt9voerrbe-LrB5hJz-0,5525
|
|
147
165
|
sglang/srt/entrypoints/openai/tool_server.py,sha256=rRNGELPV5RHONp55MYkO4_b0NPsPffJnWg-gMYwDSTc,5659
|
|
148
166
|
sglang/srt/entrypoints/openai/usage_processor.py,sha256=9LTB5rqdRuMKyZrIXiUBuF_WKaSg9X45YdzERDxbtCY,2746
|
|
149
167
|
sglang/srt/entrypoints/openai/utils.py,sha256=DT9quW0F1DX1P9NAuMxpERgXcNYKKtm7rd7J1m7EaDQ,2112
|
|
150
168
|
sglang/srt/eplb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
151
169
|
sglang/srt/eplb/eplb_manager.py,sha256=e8HMGzZb2QFRGdS7JZIFSy8cOIlxOlGRY-ef7Wei0Sw,4364
|
|
152
|
-
sglang/srt/eplb/expert_distribution.py,sha256=
|
|
170
|
+
sglang/srt/eplb/expert_distribution.py,sha256=lU1Pw8qVooiyv3LPIW1Jec09wLs22_eKdxs0kuS6vgc,32901
|
|
153
171
|
sglang/srt/eplb/expert_location.py,sha256=WoOmsZ4u9le44km3nbjJjF6BVBxN3cKRz9nQM0uWH_s,18386
|
|
154
|
-
sglang/srt/eplb/expert_location_dispatch.py,sha256=
|
|
155
|
-
sglang/srt/eplb/expert_location_updater.py,sha256=
|
|
156
|
-
sglang/srt/eplb/eplb_algorithms/__init__.py,sha256=
|
|
157
|
-
sglang/srt/eplb/eplb_algorithms/deepseek.py,sha256=
|
|
172
|
+
sglang/srt/eplb/expert_location_dispatch.py,sha256=mZUH-jvz7yvxC-5bwMFQalfKbbJiZujMiRK_M9oGOT8,4163
|
|
173
|
+
sglang/srt/eplb/expert_location_updater.py,sha256=7LOmLtY_YWYySI2GgFuTJ__Qde0LEKq70E77Q608OFU,21157
|
|
174
|
+
sglang/srt/eplb/eplb_algorithms/__init__.py,sha256=FBO0vEaWbpURbrSV6Uq753Zm2ukiCTUkDvOd292xU_E,2695
|
|
175
|
+
sglang/srt/eplb/eplb_algorithms/deepseek.py,sha256=LHEW_v5vA6FgH-oFqG4Cu113T-5ZPVdGV791MrM4K20,8293
|
|
158
176
|
sglang/srt/eplb/eplb_algorithms/deepseek_vec.py,sha256=Vzy5Iarua1VgVHzjBNZaVV_vt1LY1BLtJz7PmzB701k,10654
|
|
177
|
+
sglang/srt/eplb/eplb_algorithms/elasticity_aware.py,sha256=x6ab8G_CCaUnkFDmI6JdzQqaNIXyETW1oCsCx4PPxKY,3230
|
|
159
178
|
sglang/srt/eplb/eplb_simulator/__init__.py,sha256=HIZaXqsvsOCMMJ81dSs1afSGZ5G6OiOZEtHpltyzzjY,21
|
|
160
179
|
sglang/srt/eplb/eplb_simulator/reader.py,sha256=OlsWqsuXqVQY7PfvvrP-vsl2Ww2Kg4vD_K9BltM_QHo,1828
|
|
161
|
-
sglang/srt/function_call/base_format_detector.py,sha256=
|
|
180
|
+
sglang/srt/function_call/base_format_detector.py,sha256=pQjF8ri_i7wc8diX-sGC4FkKi6eOqSUUi39Wu2Q3-AM,15585
|
|
162
181
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
|
163
182
|
sglang/srt/function_call/deepseekv31_detector.py,sha256=hpRjjv219mH0v1PQpMvj_gezrP7PwvLiNbBKOTCSC3U,9731
|
|
164
183
|
sglang/srt/function_call/deepseekv3_detector.py,sha256=DhO3tUX1nvFlfRkHJ1Vm_7OMXFFTvWBA9u9SZKFAwuQ,9710
|
|
165
184
|
sglang/srt/function_call/ebnf_composer.py,sha256=OpjfvYowLlMLnxz5fwS7zv5-d43_ZwO9ucGAMsILvm4,15321
|
|
166
|
-
sglang/srt/function_call/function_call_parser.py,sha256=
|
|
167
|
-
sglang/srt/function_call/glm4_moe_detector.py,sha256=
|
|
168
|
-
sglang/srt/function_call/gpt_oss_detector.py,sha256=
|
|
169
|
-
sglang/srt/function_call/json_array_parser.py,sha256=
|
|
185
|
+
sglang/srt/function_call/function_call_parser.py,sha256=CXP_4OEo0M9aE3vXMW-m3VJTq9uVhM2w3NOcnnmXjuA,8762
|
|
186
|
+
sglang/srt/function_call/glm4_moe_detector.py,sha256=B4GjjgoDVc4ETyqCowfWQamIhhUDwl6pA9xsAE3sOfo,6943
|
|
187
|
+
sglang/srt/function_call/gpt_oss_detector.py,sha256=ti5Dwci_3J9XzqQetMILY7R-VTCCRbGbHas3DdC5x28,9263
|
|
188
|
+
sglang/srt/function_call/json_array_parser.py,sha256=m37S_3bQtyAI86T3ju80dkKJxuazA1VV0J5ioK1uQbw,2205
|
|
170
189
|
sglang/srt/function_call/kimik2_detector.py,sha256=VWN4Nf9l9O0uSUR0UppuoAyVObvGw-rVvklFJ1qzbRA,10641
|
|
171
190
|
sglang/srt/function_call/llama32_detector.py,sha256=trZja7IXc2IWUko5PRj7p4pRU6XCVjtxr-7qJNr0EWo,3647
|
|
172
191
|
sglang/srt/function_call/mistral_detector.py,sha256=Ts2HrJdu5r2lCCMVKPZfnCds9pt1K5H1EaOQrF_HD60,4686
|
|
@@ -174,121 +193,133 @@ sglang/srt/function_call/pythonic_detector.py,sha256=yAatItKtVDf9uhlB78wPWKP3fbe
|
|
|
174
193
|
sglang/srt/function_call/qwen25_detector.py,sha256=nv83_sipZMU6Vie3J4HeNiZVCSRU5ei7601j50779HA,5181
|
|
175
194
|
sglang/srt/function_call/qwen3_coder_detector.py,sha256=fyiF0WkNwozlKZQy0G903hj-ZAyvEgkFC8l20FVOVX8,14299
|
|
176
195
|
sglang/srt/function_call/step3_detector.py,sha256=SAibrispu0peDQzqOG2-V93KGHtV6Ud7a38vlnhTunA,17442
|
|
177
|
-
sglang/srt/function_call/utils.py,sha256=
|
|
196
|
+
sglang/srt/function_call/utils.py,sha256=P-iT81YRm1zPV7Y19bkQq5VcV15-XLF1AwoeXWI7Nig,4552
|
|
178
197
|
sglang/srt/grpc/__init__.py,sha256=dPeDsMRMW8WyHD6jolIpIlvlJsYLAhwewHhCTdu1MAE,21
|
|
179
|
-
sglang/srt/grpc/compile_proto.py,sha256=
|
|
180
|
-
sglang/srt/grpc/
|
|
181
|
-
sglang/srt/grpc/
|
|
182
|
-
sglang/srt/grpc/
|
|
183
|
-
sglang/srt/
|
|
198
|
+
sglang/srt/grpc/compile_proto.py,sha256=ZRH11Wodv4BbYo0F-JqA-ymIM-FwkkiAjwM_7msI2uA,7011
|
|
199
|
+
sglang/srt/grpc/grpc_request_manager.py,sha256=ZX4p3ewoUAd9vGG3lNKv9MknFV4BtXJQtP1u8hDJrKk,34849
|
|
200
|
+
sglang/srt/grpc/health_servicer.py,sha256=6h0JFrvVKz5hRBh3pzz_N1Hsj2WgM_Kyd7kfHuJqlDI,7278
|
|
201
|
+
sglang/srt/grpc/scheduler_launcher.py,sha256=GMuNCfF4MYYjJL3O8NqQrg1N9P7T2QyRmpxxXOAYeDw,6563
|
|
202
|
+
sglang/srt/grpc/sglang_scheduler_pb2.py,sha256=ALq0gD19OUC4CdjbOU2YYHGmgTlkJvWX3exX_SOXSv4,16016
|
|
203
|
+
sglang/srt/grpc/sglang_scheduler_pb2.pyi,sha256=ibYeIZPchbx4fcLDeAa-LSnq6MZi-mh4DgzIGg-SUWY,26274
|
|
204
|
+
sglang/srt/grpc/sglang_scheduler_pb2_grpc.py,sha256=8FQtALiqSyWkqL6P_rKerievE9q19V3675AEEomNSe8,12633
|
|
205
|
+
sglang/srt/layers/activation.py,sha256=Qg-goR7CSwQeBhS4IO56wCA7jMR_bPNZJHnLDZNnm5s,13407
|
|
184
206
|
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
|
185
|
-
sglang/srt/layers/communicator.py,sha256=
|
|
186
|
-
sglang/srt/layers/dp_attention.py,sha256=
|
|
207
|
+
sglang/srt/layers/communicator.py,sha256=dmoydeyHoiVQCr1PvMcTwM1Kirv71PZOa-JSeVD6n50,24465
|
|
208
|
+
sglang/srt/layers/dp_attention.py,sha256=dBfEtofjY9MlCDF5B-y_zrX-owfZ46mSBYioCzlIoHM,16817
|
|
187
209
|
sglang/srt/layers/elementwise.py,sha256=tGbN7bbK2s-j3DoJeJfkfyPNmKdVAutAd0J3TbxUPAQ,18849
|
|
188
210
|
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=hnVVS_VsWukTYhREubWs2KcJ1GjVMEI9ECqxqOMXZv8,6729
|
|
189
|
-
sglang/srt/layers/layernorm.py,sha256=
|
|
190
|
-
sglang/srt/layers/linear.py,sha256=
|
|
191
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
|
211
|
+
sglang/srt/layers/layernorm.py,sha256=Kf18oGBMTyqjaeeTJMeCYhyrQb-8NsSjhG0QDswM8rM,12334
|
|
212
|
+
sglang/srt/layers/linear.py,sha256=1g5vEFHqSd1TPb0VxQiZ5oga45QorYxvj2CZl_NM9wc,56084
|
|
213
|
+
sglang/srt/layers/logits_processor.py,sha256=VNMPpyxVNNXtOxd9nui0Yrm8MUkjrGBEL1cmUYXLyM0,34499
|
|
192
214
|
sglang/srt/layers/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
|
215
|
+
sglang/srt/layers/modelopt_utils.py,sha256=Abhiwmu1VOoSePJWytgFxRw_6qTtN2rqT61DPDboCIw,335
|
|
193
216
|
sglang/srt/layers/multimodal.py,sha256=vNswe0J0maeBiN8ehlmxfs-YYlrmMllYl6Nc_Y57Neg,5114
|
|
194
217
|
sglang/srt/layers/parameter.py,sha256=6ce1lx2urWJKz87g2qg_oce_S5BV0IcguSiOGGHbcC8,18378
|
|
195
218
|
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
|
196
|
-
sglang/srt/layers/radix_attention.py,sha256=
|
|
219
|
+
sglang/srt/layers/radix_attention.py,sha256=HvTa-gSz86XdN9mcK7H3lrQXjGfAMnBzI1lM8WKaIUc,5203
|
|
197
220
|
sglang/srt/layers/rocm_linear_utils.py,sha256=7PPh-5H2IYjiLp_g_szzVBsmiMacZ1RtjVtjdrdFJKI,1374
|
|
198
|
-
sglang/srt/layers/rotary_embedding.py,sha256=
|
|
199
|
-
sglang/srt/layers/sampler.py,sha256=
|
|
221
|
+
sglang/srt/layers/rotary_embedding.py,sha256=ZekORUqqnej3PP8-ETIhvlkweLMhrP1nZTH4Qz3fB-E,101467
|
|
222
|
+
sglang/srt/layers/sampler.py,sha256=bnfa0jtHBWcXeDALGGYR6t1DOejaG2LBqgG6kmXP7Fc,20632
|
|
223
|
+
sglang/srt/layers/sparse_pooler.py,sha256=9gB8duR48R-FGtA4Q7D1fIDSvbKlD70N38S3Lvg773s,3424
|
|
200
224
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
|
201
|
-
sglang/srt/layers/utils.py,sha256=
|
|
202
|
-
sglang/srt/layers/vocab_parallel_embedding.py,sha256=
|
|
203
|
-
sglang/srt/layers/attention/aiter_backend.py,sha256=
|
|
204
|
-
sglang/srt/layers/attention/ascend_backend.py,sha256=
|
|
205
|
-
sglang/srt/layers/attention/attention_registry.py,sha256=
|
|
206
|
-
sglang/srt/layers/attention/base_attn_backend.py,sha256=
|
|
225
|
+
sglang/srt/layers/utils.py,sha256=F_hhE514OZ4cyMklga3mipdUzlrKo3SolIcuqgqqQqQ,1913
|
|
226
|
+
sglang/srt/layers/vocab_parallel_embedding.py,sha256=jPZ6H45qD6ieWV2TqU65YzSaJwRWURoJQ1J-6eOOG-E,22737
|
|
227
|
+
sglang/srt/layers/attention/aiter_backend.py,sha256=bv9yGDu-4oLZlA3A00GDpOWU84cLJ97cW08aVoGEjn8,43935
|
|
228
|
+
sglang/srt/layers/attention/ascend_backend.py,sha256=lb3ZmNZmEqnmf3zng38sA48NBBLn9M9lVXW_UdB6SNw,27892
|
|
229
|
+
sglang/srt/layers/attention/attention_registry.py,sha256=OpiNS5eGkYK05lt0L6zm0NfHZFQKyI-fGtLl3wHqONk,7505
|
|
230
|
+
sglang/srt/layers/attention/base_attn_backend.py,sha256=oYk0ch5ptL2EtlhjyitKvu6H2qCHvrXSjUJVJgPnGd8,4495
|
|
207
231
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=cb2dMTnDMmMVBG_lqFRciVDiF3PeEAcXYaKDFWszeTw,9849
|
|
208
|
-
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=
|
|
232
|
+
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=wkF1GxFuLsGUWYoPWoqdz0xpePqA_nbo7xd2ha67sng,9135
|
|
209
233
|
sglang/srt/layers/attention/dual_chunk_flashattention_backend.py,sha256=20vmnq68-Cq62UWIzQU_uwJzq4B8KdJeZUPVoWPiyDs,68620
|
|
210
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
|
211
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
|
212
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
|
213
|
-
sglang/srt/layers/attention/flashmla_backend.py,sha256=
|
|
214
|
-
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=
|
|
215
|
-
sglang/srt/layers/attention/hybrid_linear_attn_backend.py,sha256=
|
|
216
|
-
sglang/srt/layers/attention/intel_amx_backend.py,sha256=
|
|
234
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=0bbODTKS-DADucy-GmR_1LQzwezvXuXGuP21Y6WH5EU,105314
|
|
235
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=R06qwUhhfeBL2qAD1CRS9KzmdoiGxO10QjAoAouNDjA,63332
|
|
236
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=LrhlHUVn0ZlvCIhK8iAjqEEqUUvRydJn7TZ7Hs4o3B4,39462
|
|
237
|
+
sglang/srt/layers/attention/flashmla_backend.py,sha256=HijFHZZ-pGE75NytFXsS0MIv8d-zWJGRRdfjdF1ViJ8,20860
|
|
238
|
+
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=_Gol1e_m6vMKhpUw2-OQ37ymC5sIuSTntDylVKSZtpA,5121
|
|
239
|
+
sglang/srt/layers/attention/hybrid_linear_attn_backend.py,sha256=tqwPna30r1zriVhKlit-iVfpfy6hJGxumGKsnlJ20C8,26119
|
|
240
|
+
sglang/srt/layers/attention/intel_amx_backend.py,sha256=8AcbJn0u8ifvhml9iocDzjrtzLEj0oJ7V7bOmkQPefo,4168
|
|
217
241
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
|
218
|
-
sglang/srt/layers/attention/nsa_backend.py,sha256=
|
|
242
|
+
sglang/srt/layers/attention/nsa_backend.py,sha256=68NXSaTzqQKL7aVSgmWgDRgPc0OYI3HNU-f9JsEV79E,45516
|
|
219
243
|
sglang/srt/layers/attention/tbo_backend.py,sha256=MyEQ29I41LCOHXm4_g7J7sXSs5bNKWRlSa2EfqploD4,9185
|
|
220
244
|
sglang/srt/layers/attention/torch_flex_backend.py,sha256=MnnZLxi41R-d4P0cyklNyefSWOU-AdFEjr8pxJWNgdI,11711
|
|
221
245
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=NdWD2ArmS1lQN9mZIbS2rcHueBWColNxvhcLaQGAKGQ,9728
|
|
222
|
-
sglang/srt/layers/attention/triton_backend.py,sha256=
|
|
223
|
-
sglang/srt/layers/attention/trtllm_mha_backend.py,sha256=
|
|
224
|
-
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=
|
|
225
|
-
sglang/srt/layers/attention/utils.py,sha256=
|
|
226
|
-
sglang/srt/layers/attention/vision.py,sha256
|
|
246
|
+
sglang/srt/layers/attention/triton_backend.py,sha256=30z1z_aJ9jUKGG3rc-2DI6h-3HO3w3hVpcFM18BVSQY,50504
|
|
247
|
+
sglang/srt/layers/attention/trtllm_mha_backend.py,sha256=IQUu3jkCuAY5foqvR6L1IYjjVD4qfmTwG6rfo05ZVkI,27516
|
|
248
|
+
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=7ceisj7_0X9mK1dDheEoVuIXHsMDjptoaw9HycBVxYQ,41679
|
|
249
|
+
sglang/srt/layers/attention/utils.py,sha256=uRyxLjpRMVesPDFtGHtzJDHQvWhS4AsGW5RGCsIYPBk,3230
|
|
250
|
+
sglang/srt/layers/attention/vision.py,sha256=-MX_K0_mX58xkpaS6O93vWIJVqha4iNgYNN5M5Yptnw,21763
|
|
227
251
|
sglang/srt/layers/attention/vision_utils.py,sha256=6hPPAt8p3SOm7tgHNUesnMLxvQiKbaOM5EK6K-ig5dI,2771
|
|
228
252
|
sglang/srt/layers/attention/wave_backend.py,sha256=dMsR7GsfDYgVizY8QJ94ASrxiiJ5_MNOuTUDDQzvpPQ,22915
|
|
229
|
-
sglang/srt/layers/attention/
|
|
253
|
+
sglang/srt/layers/attention/xpu_backend.py,sha256=nYRnYi7ZVyeC1m5WPB8TKpux2mBxCjHOzKZ5QNnCBlo,47650
|
|
254
|
+
sglang/srt/layers/attention/fla/chunk.py,sha256=r8Tddl7p0ae0nH0FU1sU3EpWTtiipdzoijaTMX3_gGI,8913
|
|
230
255
|
sglang/srt/layers/attention/fla/chunk_delta_h.py,sha256=Gf8RgLesGaR9GM4HTB7kDDCVirwR9XvO7O3I1HWdcuY,10681
|
|
231
|
-
sglang/srt/layers/attention/fla/chunk_o.py,sha256=
|
|
256
|
+
sglang/srt/layers/attention/fla/chunk_o.py,sha256=ngvGxIxeHhulkj_FfQgtNY0T-5cwV_4Ochc_6dP6oVo,4973
|
|
232
257
|
sglang/srt/layers/attention/fla/chunk_scaled_dot_kkt.py,sha256=445twkm9l0Mu9Q_VFBIgUZQzTNLvc82gqIAe8ylip-4,4386
|
|
233
258
|
sglang/srt/layers/attention/fla/cumsum.py,sha256=beIT2WTSn8Wk_wknoWM3JYQhzmzR1JJwMFzspsXvWng,8374
|
|
234
259
|
sglang/srt/layers/attention/fla/fused_recurrent.py,sha256=yOSTwqcNSoPWwQD--tcCkVd2OwB5Ox0nLGnLLv8MRr8,20856
|
|
235
260
|
sglang/srt/layers/attention/fla/fused_sigmoid_gating_recurrent.py,sha256=dlmOu-7DG6YoSNexT3YV8GudrFPn_RiYj-3hClWdy-c,6424
|
|
236
|
-
sglang/srt/layers/attention/fla/index.py,sha256=
|
|
261
|
+
sglang/srt/layers/attention/fla/index.py,sha256=u4yVogS7a2DrfsYwQ22t60DpO3Y7KF9eAHY1PUrfUt4,989
|
|
237
262
|
sglang/srt/layers/attention/fla/l2norm.py,sha256=XOs5nGdWROp3FW4fHSObC8sa_x697yDV0jt5UKuLllE,3783
|
|
238
|
-
sglang/srt/layers/attention/fla/layernorm_gated.py,sha256=
|
|
263
|
+
sglang/srt/layers/attention/fla/layernorm_gated.py,sha256=OJEzBNg4JQ6_Vk_ZHWnVPwy8PLbrwuBiw3rt9bLiBRc,10122
|
|
239
264
|
sglang/srt/layers/attention/fla/op.py,sha256=Qc-zHwZY9-8Aw53AuuzNfpbPBwKgIvVMgtWcfJLl6A4,1695
|
|
240
265
|
sglang/srt/layers/attention/fla/solve_tril.py,sha256=-Z51hFsLER_Lzn8h21WRUajbVOA1wuu5TSEvaC2AvK8,14405
|
|
241
|
-
sglang/srt/layers/attention/fla/utils.py,sha256=
|
|
242
|
-
sglang/srt/layers/attention/fla/wy_fast.py,sha256=
|
|
243
|
-
sglang/srt/layers/attention/mamba/causal_conv1d.py,sha256=
|
|
244
|
-
sglang/srt/layers/attention/mamba/causal_conv1d_triton.py,sha256=
|
|
245
|
-
sglang/srt/layers/attention/mamba/mamba.py,sha256=
|
|
246
|
-
sglang/srt/layers/attention/mamba/
|
|
266
|
+
sglang/srt/layers/attention/fla/utils.py,sha256=CxcsCXLamjIhbCuj3NUqar1LasPsGGf8WX4acXnF_fE,10451
|
|
267
|
+
sglang/srt/layers/attention/fla/wy_fast.py,sha256=wS1sJq23pa5xK2tUDYRO5FhLLJ5JpHWozBghDl64pYY,4284
|
|
268
|
+
sglang/srt/layers/attention/mamba/causal_conv1d.py,sha256=0Im_XzEA965rT5r09-bm1We1BaPgq2g_yo5nbA7KwvI,4503
|
|
269
|
+
sglang/srt/layers/attention/mamba/causal_conv1d_triton.py,sha256=EqiIga4XzikCKeA9wvLAcK3uTCX-Fop9GQFyzLeNAg4,37660
|
|
270
|
+
sglang/srt/layers/attention/mamba/mamba.py,sha256=qGGEzMVZDDG0dEdUrLxVfWhRa1UI5OLis7dVBMqUpl0,22517
|
|
271
|
+
sglang/srt/layers/attention/mamba/mamba2_metadata.py,sha256=6hkbWuV0do1lFXucgGusqR5ha784g5CB7P7hZaigRNM,8551
|
|
272
|
+
sglang/srt/layers/attention/mamba/mixer2_rms_norm_gated.py,sha256=C60rddCKuf3eD6KVt5vB60LlGD2dYiU9WZGTlEPaoDM,4689
|
|
247
273
|
sglang/srt/layers/attention/mamba/ops/__init__.py,sha256=r-IpDGRIwTqGJzZoWNGyHqsqqv8oF19pNHEb7_TZR9M,98
|
|
248
274
|
sglang/srt/layers/attention/mamba/ops/layernorm_gated.py,sha256=hmuL7vQ77aWFENCDsJDB7Nki5DDdMTEiQywbaU4FC04,5229
|
|
249
275
|
sglang/srt/layers/attention/mamba/ops/mamba_ssm.py,sha256=aCFsiBdBDYt3D5HT0lxt6Rru9-gPYZspBM_WpTGgHh4,13680
|
|
250
|
-
sglang/srt/layers/attention/mamba/ops/ssd_bmm.py,sha256=
|
|
251
|
-
sglang/srt/layers/attention/mamba/ops/ssd_chunk_scan.py,sha256=
|
|
252
|
-
sglang/srt/layers/attention/mamba/ops/ssd_chunk_state.py,sha256=
|
|
253
|
-
sglang/srt/layers/attention/mamba/ops/ssd_combined.py,sha256=
|
|
254
|
-
sglang/srt/layers/attention/mamba/ops/ssd_state_passing.py,sha256=
|
|
255
|
-
sglang/srt/layers/attention/npu_ops/mla_preprocess.py,sha256=
|
|
276
|
+
sglang/srt/layers/attention/mamba/ops/ssd_bmm.py,sha256=IGOJ67TLx2WQQwDFm9jw2OU8vTZc0daVUnQF6kcu2x4,6798
|
|
277
|
+
sglang/srt/layers/attention/mamba/ops/ssd_chunk_scan.py,sha256=n70BQM8Dpg7_shX87ay3QvBEUO4fEcmg1OopU88KPiE,18405
|
|
278
|
+
sglang/srt/layers/attention/mamba/ops/ssd_chunk_state.py,sha256=Qdzx_4DIwl1-g_c24lRWKfmLTL29rxn2aRELWfuUct0,20784
|
|
279
|
+
sglang/srt/layers/attention/mamba/ops/ssd_combined.py,sha256=evYcNq31qo1TeaJP8Q3yttBQODici594N4kpdgT7hrQ,8880
|
|
280
|
+
sglang/srt/layers/attention/mamba/ops/ssd_state_passing.py,sha256=pNjxxLYw2BsTwy5-m7RhgqTZ9H8uyQFX2GQVucWU4wE,10032
|
|
281
|
+
sglang/srt/layers/attention/npu_ops/mla_preprocess.py,sha256=3_jiUFd2um4mOwG2FaNHWfwbRbjko0c6EeDfdlUiGO4,14554
|
|
256
282
|
sglang/srt/layers/attention/nsa/dequant_k_cache.py,sha256=ie1qLy7AAipFYS0EJFrunN8Mq97D9v-noWaJBYMiv0I,4973
|
|
257
283
|
sglang/srt/layers/attention/nsa/index_buf_accessor.py,sha256=jPYRgFfTdH_g83OUs9q3ncj2Y036ikBvflMjYEjrHGw,11481
|
|
258
|
-
sglang/srt/layers/attention/nsa/nsa_indexer.py,sha256=
|
|
284
|
+
sglang/srt/layers/attention/nsa/nsa_indexer.py,sha256=qTzO557wWrB7RypNvX1i5_C5vr66X_YPjEgJiV_TP3E,25368
|
|
259
285
|
sglang/srt/layers/attention/nsa/quant_k_cache.py,sha256=FYl6gp16uGU3ftIHkU5vFAjfdPnoKvWOg4l7TBKkGI4,8675
|
|
260
286
|
sglang/srt/layers/attention/nsa/tilelang_kernel.py,sha256=Iifd9YYEnDGkRhjK0NH-pbyTiQX0kVpJynyGwZcnH8w,31554
|
|
261
287
|
sglang/srt/layers/attention/nsa/transform_index.py,sha256=0yurXIDt5EQ9k_P5g_aDXohdzvSiBQcQpCHBcNf0ZBA,4745
|
|
262
|
-
sglang/srt/layers/attention/nsa/
|
|
288
|
+
sglang/srt/layers/attention/nsa/triton_kernel.py,sha256=FyInDj54ux1IctSGlPd82iq-aGY-UfXJvd1KIPO9LTI,3974
|
|
289
|
+
sglang/srt/layers/attention/nsa/utils.py,sha256=_Ni-gYZTx5MXbIV2i5-7MexX6N5vsZNYTY-b0GczXRI,822
|
|
263
290
|
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=JnOtqtPXEgn_T0R4gGCROx1szlAhu_G_ODNKCazz0lE,20554
|
|
264
|
-
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=
|
|
265
|
-
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=
|
|
291
|
+
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=TGnhUIoTsrFmOAVspsGpG0F_ORB7EMahM4v7nl7tNoQ,31105
|
|
292
|
+
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=KzkbTOStDiIb76i5F7yLRZL0ThuZdBzv290KB2FZDow,32920
|
|
266
293
|
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
|
267
294
|
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
|
268
295
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
|
269
296
|
sglang/srt/layers/attention/wave_ops/decode_attention.py,sha256=oJNBG57cySgxtmJe1MSEsZKOIQOXnH0iVAcFO6DUWvY,4732
|
|
270
297
|
sglang/srt/layers/attention/wave_ops/extend_attention.py,sha256=LyZQQIvFYfcIcObgy_tETK5JxRLgAkOYlF-KhGcGEoA,3877
|
|
271
298
|
sglang/srt/layers/attention/wave_ops/prefill_attention.py,sha256=viTUit0rxjVV5UahuwmVAhmL66YRFJD4g1YhH_oRBu8,2344
|
|
299
|
+
sglang/srt/layers/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
|
300
|
+
sglang/srt/layers/deep_gemm_wrapper/compile_utils.py,sha256=tvoJ2PmYJWm6j_JfRpmBhg7mUZyH27f5JJeDZ4xcZhg,8067
|
|
301
|
+
sglang/srt/layers/deep_gemm_wrapper/configurer.py,sha256=vkMBNZx3RqukEtxMUAbTfKJii3MDXLBs83ZlsgtxNiU,559
|
|
302
|
+
sglang/srt/layers/deep_gemm_wrapper/entrypoint.py,sha256=5VTBfCU6wTBS2uMJc-luyqawh1478w3Jh1qk39qhjlI,3199
|
|
272
303
|
sglang/srt/layers/moe/__init__.py,sha256=P8OC-pUE5yeEr80QUDqSPwF9a9BAYPuaK7GNlQovsJw,863
|
|
273
|
-
sglang/srt/layers/moe/cutlass_moe.py,sha256=
|
|
304
|
+
sglang/srt/layers/moe/cutlass_moe.py,sha256=335MeGbcVPsAI9oaEQCVSMxzzQ9YV1qPiNxINXtvO48,14206
|
|
274
305
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
|
275
|
-
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=
|
|
276
|
-
sglang/srt/layers/moe/flashinfer_cutedsl_moe.py,sha256=
|
|
306
|
+
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=yTSlr_B9y1jiAmp6pX88LHb7hQ351Ensa8SR2fgW3v8,13898
|
|
307
|
+
sglang/srt/layers/moe/flashinfer_cutedsl_moe.py,sha256=ULLAdfRad_sG2ZYXE4qMCOutQX0eckQt0fwwhfcsckA,6186
|
|
277
308
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=XzJPM9Z6YQ4ejrMrBFt3l1i7guBcdQTXo9-gT5H8AIA,3479
|
|
278
|
-
sglang/srt/layers/moe/rocm_moe_utils.py,sha256=
|
|
279
|
-
sglang/srt/layers/moe/router.py,sha256=
|
|
280
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
|
281
|
-
sglang/srt/layers/moe/utils.py,sha256=
|
|
309
|
+
sglang/srt/layers/moe/rocm_moe_utils.py,sha256=SglTXIzpiWKFKVEf9gS8SEocJYcSOmeKUKjHznfC_nI,4527
|
|
310
|
+
sglang/srt/layers/moe/router.py,sha256=ouSNu8XU2w-BICyAYPpFq2zPb11LyTDalZElh0AXGus,13675
|
|
311
|
+
sglang/srt/layers/moe/topk.py,sha256=reUXYWZdHVfNJnrRxd8kXjGVLhdNu3AxRqOt5N7NyGg,32306
|
|
312
|
+
sglang/srt/layers/moe/utils.py,sha256=lP4WESNZBjCaY-dOnuJ6jkrrAXl2e3pR3MTMjyWQFic,6782
|
|
282
313
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
283
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
|
284
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
|
314
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=DjgEBHIS8-S1SO46xGbnREc2vQ8dO9dDKNRYKZuwMzM,32125
|
|
315
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=D8U42eegm1cwuS9zpwIOj_DV_LmiapMOh2hMWJOBWj8,26193
|
|
285
316
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=tis0ZJmih7gKHCurbLtY_o-bY3K4MOzQLYLC3ftIOf0,977
|
|
286
317
|
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=mKH6zTTuh_Z8Ceg6d1VWjGBI3iPBn1YfGO6udxIRAtU,23306
|
|
287
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py,sha256=
|
|
318
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py,sha256=0jTqnuw8v6uwr4g2IJ6bc3PRq77HF96mEYaSOBmpTAQ,7983
|
|
288
319
|
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py,sha256=QOdl5uhZ8--aryXnKObdspKonGcF6Tc_U9o_lC_opo8,27760
|
|
289
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
|
320
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=E2qURbonpdnEOqEV2MmgLgUdecCSyfxyua3rmWb5kiI,39806
|
|
290
321
|
sglang/srt/layers/moe/fused_moe_triton/moe_align_block_size.py,sha256=U93mxPPU2RP7d3QRSvoG3OCtUQIK8YhQfHf1ZGeREmY,3284
|
|
291
|
-
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=
|
|
322
|
+
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=8_LiuVJqeuMIsy0nBJExYH9RAftfyutCKh_2NWU10rg,10141
|
|
292
323
|
"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
|
|
293
324
|
"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
|
|
294
325
|
"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
|
|
@@ -473,6 +504,7 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
|
473
504
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=385,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=rgF-KSAUXmI7QGrhMUywPVfeTxz_j8_IP4N-6bkYdak,3260
|
|
474
505
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=385,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=7aaoi0MI2xC5ZJkflkTZAH4tawTPdmUpmcBOgOInKxs,3268
|
|
475
506
|
"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
|
|
507
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=-MZaZ4R9r5Rk8a9OEa1eM_S6INlcsX68Bj5_pM4Aa0U,3257
|
|
476
508
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=352,device_name=NVIDIA_RTX_5880_Ada_Generation,dtype=fp8_w8a8.json",sha256=L7acUMDmYZOeA-riEds1-r9Wsq2KBWJlG7X7rilWjfA,3254
|
|
477
509
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=6JYGN4imwzIrQAEgboSO93wWYBuguzTgBjfTedq2c_Q,3250
|
|
478
510
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=ClPogINm5AsnjDqx6Hz_rHrmnnCdUPid-jYIdIgjZxs,3250
|
|
@@ -480,6 +512,7 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
|
480
512
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=W8C1GtP4K43SK9128U52DD5WWofvPleAJE4us2Qju1k,3251
|
|
481
513
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=161,N=384,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Max-Q_Workstation_Edition,dtype=fp8_w8a8.json",sha256=RMYwqtB7hYeaCyuZ1feVnRhBGlN4jMcmNQX2hqUqBlk,3254
|
|
482
514
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=T6kCtCUytCxiW8JOLfEF3YgdCD9_mKccJ85IqT0b8LU,3253
|
|
515
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_B200.json",sha256=NkLVci5u2GGeuFbC3d_6PicBS3mSuV77JICCSzU_8cc,3238
|
|
483
516
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_H800,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=M3W1OQU6RgKAQL2EoYivAIidtz1cvgoK6_6ntNfn_lY,3265
|
|
484
517
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=512,device_name=NVIDIA_H20.json",sha256=bSe-KUwiVT3yM9jQuXlDmxe_KUft7FUn5zOby8bpSkc,3233
|
|
485
518
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=RbJYTRfjP_3-ytfj53W_w2jFpZ9xwMaqoKW52pkgP3c,3257
|
|
@@ -496,49 +529,52 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
|
496
529
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=64,device_name=NVIDIA_H200.json",sha256=phmhkQNz8DcLHPqN5tjmJqOgbX0BhQx9cP82fp_jyIQ,3236
|
|
497
530
|
sglang/srt/layers/moe/moe_runner/__init__.py,sha256=Dc4PH6HfzQDjJWL7iuZ-0qh8oRu7OtnH6IEl675pYiU,172
|
|
498
531
|
sglang/srt/layers/moe/moe_runner/base.py,sha256=GMdFI74BGO5HDjtel5QWI7W4CFix0BHkw_HrjVswhcw,8905
|
|
499
|
-
sglang/srt/layers/moe/moe_runner/
|
|
500
|
-
sglang/srt/layers/moe/moe_runner/
|
|
501
|
-
sglang/srt/layers/moe/
|
|
502
|
-
sglang/srt/layers/moe/token_dispatcher/
|
|
503
|
-
sglang/srt/layers/moe/token_dispatcher/
|
|
504
|
-
sglang/srt/layers/moe/token_dispatcher/
|
|
505
|
-
sglang/srt/layers/
|
|
506
|
-
sglang/srt/layers/
|
|
507
|
-
sglang/srt/layers/quantization/
|
|
508
|
-
sglang/srt/layers/quantization/
|
|
532
|
+
sglang/srt/layers/moe/moe_runner/deep_gemm.py,sha256=xhxZsQpD9U8OReNaA_qwXWA98hVUS6rvcbWukQcv8tc,9342
|
|
533
|
+
sglang/srt/layers/moe/moe_runner/runner.py,sha256=MCrPZQuuTxD4NGdnRaIkLc-xy8yOnXZW3ThJ2L-ymu4,2845
|
|
534
|
+
sglang/srt/layers/moe/moe_runner/triton.py,sha256=pYzFyJDocnBfNiF6kp1cnSZmKKTsLOYXpAUXFZYKOsI,14464
|
|
535
|
+
sglang/srt/layers/moe/token_dispatcher/__init__.py,sha256=0lIB1lkEcVYiW2iEL_hzAPk-AG85dFYAdyK9MBftHsw,1273
|
|
536
|
+
sglang/srt/layers/moe/token_dispatcher/base.py,sha256=ZisVo2ty9vx5Oj1V1_w570_v8e8zbIpcEeXl4UUeZVQ,4015
|
|
537
|
+
sglang/srt/layers/moe/token_dispatcher/deepep.py,sha256=lVBM2ZE4XgHX4eqVuFuoF5rPPrY54CKoiapa3txFvcc,26430
|
|
538
|
+
sglang/srt/layers/moe/token_dispatcher/mooncake.py,sha256=ZQpjlv-WvEvTgFE6R_zuzFZXOfbRwVvXFYpOnWuCBXk,11855
|
|
539
|
+
sglang/srt/layers/moe/token_dispatcher/standard.py,sha256=2il92nCW6HuuUrkT9MHumTQf0FZ-JhVBoWNzwaZ_Zwo,3461
|
|
540
|
+
sglang/srt/layers/quantization/__init__.py,sha256=f05hWlwXrtzH0Ugk4kY6xofrnMK4A63FbSyPj5GMi6w,6343
|
|
541
|
+
sglang/srt/layers/quantization/awq.py,sha256=jeGGkHIkmRsGHNWo27uNPB7B6M1uYSVmmjeCbhdIjew,33411
|
|
542
|
+
sglang/srt/layers/quantization/awq_triton.py,sha256=1QwpxPoqcfe3sDU8uRs3LXBRcDZvq-M9xQ7NE9RV0Mc,12658
|
|
543
|
+
sglang/srt/layers/quantization/base_config.py,sha256=v9apbnLDBUqQfm67kAYeky1Fe_RVyi1Upeua1w1ncK8,7895
|
|
509
544
|
sglang/srt/layers/quantization/blockwise_int8.py,sha256=pqSLo4gwazZ4ajdVzyouwh_Z5oVDbWq9wo8RnrMdY8o,13998
|
|
510
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
|
511
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=
|
|
512
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=
|
|
513
|
-
sglang/srt/layers/quantization/fpgemm_fp8.py,sha256=
|
|
514
|
-
sglang/srt/layers/quantization/gptq.py,sha256=
|
|
515
|
-
sglang/srt/layers/quantization/int8_kernel.py,sha256=
|
|
545
|
+
sglang/srt/layers/quantization/fp8.py,sha256=pyJxdl5jrXjzup27BI2hmIqKic_S9qI0siMR5qL_XeY,53442
|
|
546
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=noTju6oEzKQ4mOcgWF8s0sFL5g-PuxLrCivvSbKQJWI,56181
|
|
547
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=enZUimrleDg7RJhoh7uxVLRYd1dSMKeCUhaXuwWAYyE,29831
|
|
548
|
+
sglang/srt/layers/quantization/fpgemm_fp8.py,sha256=OpDJAOBpy3PtAvDwG3ZIA4ItMFvrodxAHTkHQnT_cso,6967
|
|
549
|
+
sglang/srt/layers/quantization/gptq.py,sha256=oAlxR3qX06Pwc9-kkrzu7W4j0K-zWfi2JQL3yO0HHCI,39377
|
|
550
|
+
sglang/srt/layers/quantization/int8_kernel.py,sha256=nl3bmwcgvs8SCe3_jz0hC5f6HfdohhEMyeWM_t8Zx5Q,13124
|
|
516
551
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
|
517
552
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
|
518
|
-
sglang/srt/layers/quantization/marlin_utils.py,sha256=
|
|
553
|
+
sglang/srt/layers/quantization/marlin_utils.py,sha256=Zvasw0DpgMQKTNJm1ZNGLt3P1AKgDfYhTpePdI9BbQ4,26634
|
|
519
554
|
sglang/srt/layers/quantization/marlin_utils_fp8.py,sha256=iSjq-ikPOTU5plrWNTW4MletKLySIrNl5NhQmY6FyAo,12508
|
|
520
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
|
555
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=yKs6xczPfjKV1UKB5S50nol4rRURMX4m7_7pYIYJZU4,60689
|
|
521
556
|
sglang/srt/layers/quantization/moe_wna16.py,sha256=uoRhxJ8W_U_VFpbn03YEp0aCjbzqquWwonjuN7KBucw,19117
|
|
522
|
-
sglang/srt/layers/quantization/mxfp4.py,sha256=
|
|
557
|
+
sglang/srt/layers/quantization/mxfp4.py,sha256=OpthUaglm7Yf9jojZenHqRSVLWLy3mFuGk6PvgPNsnQ,31829
|
|
523
558
|
sglang/srt/layers/quantization/mxfp4_tensor.py,sha256=bGeCXlIOhmFZFGWp_lITkIRDEgGUaLpawDvMy1cTOmA,5389
|
|
524
|
-
sglang/srt/layers/quantization/petit.py,sha256=
|
|
559
|
+
sglang/srt/layers/quantization/petit.py,sha256=foRPfOfhq02h6yMt-8yHKofQB6l16Pz-bRCqUD3iiHU,8944
|
|
525
560
|
sglang/srt/layers/quantization/petit_utils.py,sha256=-gy4zMhqNoIA1R0n7-5C0efV54jHonCUgPDUUFjGsyM,3245
|
|
526
561
|
sglang/srt/layers/quantization/qoq.py,sha256=jM96uJfKz3vo1B6SSIrQXNT3vnD3UJrepK2eY-tSQU4,8139
|
|
527
562
|
sglang/srt/layers/quantization/rocm_mxfp4_utils.py,sha256=Z4pYWl6ExOXq2qfTHorW16hVbJ-Rk4G8Wrxn_x8boHE,327
|
|
528
|
-
sglang/srt/layers/quantization/unquant.py,sha256=
|
|
529
|
-
sglang/srt/layers/quantization/utils.py,sha256=
|
|
530
|
-
sglang/srt/layers/quantization/w4afp8.py,sha256=
|
|
563
|
+
sglang/srt/layers/quantization/unquant.py,sha256=T-KbIdvsYSqNdYfdnH7zSy9foSHMagPcFLfxkfF8e_g,15980
|
|
564
|
+
sglang/srt/layers/quantization/utils.py,sha256=yqgmoLvrrp5aRj-LTJZ6dI1hmP1UFgbpyjVWJJdomZQ,18472
|
|
565
|
+
sglang/srt/layers/quantization/w4afp8.py,sha256=yYvI7Tv4N3urK4m6QyO6cWa-SBz7bN6bZREnDqwX4wg,12969
|
|
531
566
|
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=ugLV4G4MDog-UuLqSnEasBqE3Hh6AqE5ZYI371ean90,10415
|
|
532
|
-
sglang/srt/layers/quantization/w8a8_int8.py,sha256=
|
|
533
|
-
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=
|
|
534
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=
|
|
535
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
|
567
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=WkhbRVnEamh78uyj9WyS9OfeSpZTsWh51kDCH4HICa4,37534
|
|
568
|
+
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=zMpLnf9GiRhV-jg1H2UiZ6OUMSKMcmLtrr2A4XjhuUs,217
|
|
569
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=P8RmY91K2a__xNQI69zqTuGFnFCBE41DGUlp9WutKJQ,24948
|
|
570
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=yUITBLC024lXAkVh3qfvd6bX_U0prVMbX4me_gtqUWI,38895
|
|
536
571
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
|
537
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=
|
|
572
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=qhx1YhMH6dzvnzLSSN1uQDE3wDHMoOA_HRkjn6lsvzU,589
|
|
538
573
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
|
539
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=
|
|
574
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=kDkks4z5zCh3bBoAo0_I3Yyp0--a_sQBY2zNs2wzJ0w,4982
|
|
540
575
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=4cfB6pv7kt8Ek0e88vLyXymSW6VqbAUpIjNt_-KK9-M,6318
|
|
541
576
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py,sha256=6usNdpr8mL5QRlTK_pZQtGwgmSMNi0KdMfm57kq3lw0,6908
|
|
577
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py,sha256=uG3dvlNuP5ZC3_NxIhjWWkrUVw4FQxlt5jobzaofAHM,12884
|
|
542
578
|
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=RdHQxWXwXqvio31192vsLaKjEr4f_DjpMPKlarY1IAk,3251
|
|
543
579
|
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=0vLaJgo5B9ti-XMFKJuvSoMGjsZQ-RhHSx4cC8Xji-U,3254
|
|
544
580
|
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=tkLjwLC_aVXhzuvo-2QHkojXZauPJsf3jNHFn1S7uRA,3244
|
|
@@ -691,325 +727,348 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
|
691
727
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=PD4AJYCkHfy2ivv9baMouFXzBTy0eKMumbAfxfm91HI,3256
|
|
692
728
|
"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
|
|
693
729
|
"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
|
|
694
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
|
695
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=PI9r3PHCMK9EgpoFuBgR4jvokA5sBz8zyC47ps3wet4,8164
|
|
696
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=a1b2P8-5PRNwW1ykXR7jJF94aUF3u3t3P9ad_R1k2PI,549
|
|
697
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=qiUuQn-InDLYVNDPFOxde2XB-qlE0fol0HPTkY5KN8g,3197
|
|
698
730
|
sglang/srt/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
699
|
-
sglang/srt/layers/quantization/quark/quark.py,sha256=
|
|
700
|
-
sglang/srt/layers/quantization/quark/quark_moe.py,sha256
|
|
731
|
+
sglang/srt/layers/quantization/quark/quark.py,sha256=Xt8e8Ds7wKV2UyQ3rJq9cFUtSNmTSAnRLnC2OgTBLds,14687
|
|
732
|
+
sglang/srt/layers/quantization/quark/quark_moe.py,sha256=-XW9mKSisXmqs7Ep9exPAFlGgCfZ0-N3P35B9HZdamA,7371
|
|
701
733
|
sglang/srt/layers/quantization/quark/utils.py,sha256=zZHRe9mjxGp16_OJ5Qy_UtnQgipl3ZRZUmruYvyEm_w,7445
|
|
702
734
|
sglang/srt/layers/quantization/quark/schemes/__init__.py,sha256=z1LHBPqkxAS6Wp70DWwESOSixWpIhIQwz1IHcWDdURQ,167
|
|
703
735
|
sglang/srt/layers/quantization/quark/schemes/quark_scheme.py,sha256=b8-Djo-UQAwgxSWViKDoEP5dOSesnEBPyozX-osB3WY,1478
|
|
704
|
-
sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=
|
|
736
|
+
sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=aASlSjoLgmEmiSAULaehpNOCSGy1OYiAFazWLmJB970,3935
|
|
737
|
+
sglang/srt/lora/eviction_policy.py,sha256=IaG1tlchPeT2iYwuaMGdHuma91wraO1K9qRIFoV4yko,5378
|
|
705
738
|
sglang/srt/lora/layers.py,sha256=0XlVcBTT1InMsBoLfiOO7yOnlDrnpXD_08wKo84T4B4,11852
|
|
706
739
|
sglang/srt/lora/lora.py,sha256=FooB4hOW5uvZJrDrdqKwBExb-lX5Uw_Y1gjU9an8hzc,7669
|
|
707
740
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
|
708
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
|
709
|
-
sglang/srt/lora/lora_registry.py,sha256=
|
|
710
|
-
sglang/srt/lora/mem_pool.py,sha256=
|
|
741
|
+
sglang/srt/lora/lora_manager.py,sha256=WkSFWbyWtR2jkG7Erled9PBLTMqkB3keVjaN31Cluq8,19950
|
|
742
|
+
sglang/srt/lora/lora_registry.py,sha256=Ox1n6ZmGAWGThpDVd8WjQbJACejnA8n2lGNCVzKReaQ,8173
|
|
743
|
+
sglang/srt/lora/mem_pool.py,sha256=WQex5E9lQ2Arzkc9X52EHx3OLWzMwQfoepv3OdL7Fv0,12412
|
|
711
744
|
sglang/srt/lora/utils.py,sha256=FeIb51m5EIcetP1Pgn8X17EfuE5tGipm5iurRg3RAZw,4424
|
|
712
745
|
sglang/srt/lora/backend/base_backend.py,sha256=kfkr-OxdPyUwMzi0HgjTNfX9bZC4z_ljt3srzRPgMfI,6139
|
|
713
746
|
sglang/srt/lora/backend/chunked_backend.py,sha256=x2VNkjLHmrOXwI67v_2LgjpCH8R5wuSmY5jdTWV4K7g,12701
|
|
714
|
-
sglang/srt/lora/backend/triton_backend.py,sha256=
|
|
747
|
+
sglang/srt/lora/backend/triton_backend.py,sha256=XrOaZLlwldwvGjE1h0OOVKIwYIS98Ph0aWQetub3udo,6026
|
|
715
748
|
sglang/srt/lora/triton_ops/__init__.py,sha256=no7N7uWnmCvHHbNZ6PZEadXDujIjHGP2jp_3N9j6vHM,495
|
|
716
|
-
sglang/srt/lora/triton_ops/chunked_sgmv_expand.py,sha256=
|
|
717
|
-
sglang/srt/lora/triton_ops/chunked_sgmv_shrink.py,sha256=
|
|
749
|
+
sglang/srt/lora/triton_ops/chunked_sgmv_expand.py,sha256=rllqrhX3NQTmFNXnfxm0v7sY06-hggZkNWIjU9TRBc4,6844
|
|
750
|
+
sglang/srt/lora/triton_ops/chunked_sgmv_shrink.py,sha256=n5ANXoEciOFgXuQkRZzZcW1WmdV2qtFDH7Yx83GYHUA,5462
|
|
718
751
|
sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=QURCYxHNR8Ls4SQtt3dvdgjvdDVhywI9tOzsK8SV9m8,5779
|
|
719
752
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=z9BB84Xu_MjwCu5v9Yvji-FkIzfEjDySAFybc4WYv7A,6483
|
|
720
753
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=Ksova04wgeGsFqGOXWqJtMYaHgyUYcx8VU42BZQOkVA,5129
|
|
721
754
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=VqCAFvUtq_l-0RGIkx3W_fzD55QcW2FAcqpvSHOBFp4,5115
|
|
722
755
|
sglang/srt/managers/async_dynamic_batch_tokenizer.py,sha256=btIWhI15a3QCLabdZZhrJVEWZ3zZTgldbv7pGjAPZqo,7236
|
|
723
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
|
756
|
+
sglang/srt/managers/cache_controller.py,sha256=Wy0ygZ5FAiXLrz1xzczeinfJATk7aPkH6yvXqOzH5_A,30478
|
|
724
757
|
sglang/srt/managers/configure_logging.py,sha256=8sNXZ2z9pBWOwn-X3wyz013Ob8Nbm1zDxRkxoZjH-l4,1633
|
|
725
|
-
sglang/srt/managers/data_parallel_controller.py,sha256=
|
|
726
|
-
sglang/srt/managers/detokenizer_manager.py,sha256=
|
|
758
|
+
sglang/srt/managers/data_parallel_controller.py,sha256=TAJErsNQUomHFnekrPceMZbN95PfFadticjSup3JiLY,19236
|
|
759
|
+
sglang/srt/managers/detokenizer_manager.py,sha256=K6TLeBtDb8geRVKvTlFqZJN-26saYJxxLlRspvEOFe8,13080
|
|
727
760
|
sglang/srt/managers/disagg_service.py,sha256=7VyRva5oniAPs8G-DYg2fv-mdjSxk9cLZPzl_TmB_2Q,1588
|
|
728
|
-
sglang/srt/managers/io_struct.py,sha256=
|
|
729
|
-
sglang/srt/managers/mm_utils.py,sha256=
|
|
730
|
-
sglang/srt/managers/multi_tokenizer_mixin.py,sha256=
|
|
761
|
+
sglang/srt/managers/io_struct.py,sha256=BEx_N4PwZnLoTBdvMp_zHz29btJvUevTM7S5gqVeB5k,50778
|
|
762
|
+
sglang/srt/managers/mm_utils.py,sha256=xJ7Pbk1ZxIyodLyeNv_t0JeSKCqrP7u5hpMcC-0Rpzc,31283
|
|
763
|
+
sglang/srt/managers/multi_tokenizer_mixin.py,sha256=nz_G1sLW-bN8Aa7Vy4ZUM7voaCPf7oMTe_M76H7vhyE,21050
|
|
731
764
|
sglang/srt/managers/multimodal_processor.py,sha256=0mLkwu6CGRQtt3G2T1tS3PSsh6dpyivV-vAfIHfcMbQ,1764
|
|
732
|
-
sglang/srt/managers/overlap_utils.py,sha256=
|
|
733
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
|
734
|
-
sglang/srt/managers/schedule_policy.py,sha256=
|
|
735
|
-
sglang/srt/managers/scheduler.py,sha256=
|
|
765
|
+
sglang/srt/managers/overlap_utils.py,sha256=dDz1zUBlJ9Ohw4TPHgOxnuh6LPCsN037c14XIw3E-J8,5050
|
|
766
|
+
sglang/srt/managers/schedule_batch.py,sha256=0oWPNVtdgoX2bFHOc1RN_1IYyoIE1yKwCImll65dAbQ,72622
|
|
767
|
+
sglang/srt/managers/schedule_policy.py,sha256=BFWoHG3m-lkeVvOkLGoMeEbRplq4vF4thsjv-P8MG84,28818
|
|
768
|
+
sglang/srt/managers/scheduler.py,sha256=BQ3_X5uG2a9La955Mw8OGTrhhlgKkhe3nDUE006YVnU,114768
|
|
736
769
|
sglang/srt/managers/scheduler_input_blocker.py,sha256=SYZ91JNTHtqiBHUpkk_MboAiBFyl5U7ardLcYDAQ0OU,3689
|
|
737
|
-
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=
|
|
738
|
-
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256
|
|
739
|
-
sglang/srt/managers/
|
|
770
|
+
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=duFJs6DlSFzV_1c7R2ESNGFEkGekxgDziJns4ttK-0Y,14962
|
|
771
|
+
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=n6zvLqu-TpTaZuWfYxz7ivCBPP3Z7okTOOshTq0d4CQ,42449
|
|
772
|
+
sglang/srt/managers/scheduler_pp_mixin.py,sha256=oUl5oxbFPd2gxqn4JXk-Bn-uLrmJZ6_Km5SMpSe9Gtk,16433
|
|
773
|
+
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=LKgAaQ9kNdjK7J6xSwQQzo2q_pViWnlGIvTpe5_yLLQ,13505
|
|
740
774
|
sglang/srt/managers/scheduler_recv_skipper.py,sha256=8rVQCBjn9f26Th4XbeUS3fEsvo1GI029Me28wMjcKRY,1103
|
|
741
|
-
sglang/srt/managers/
|
|
775
|
+
sglang/srt/managers/scheduler_runtime_checker_mixin.py,sha256=54z5p36M2BgTQYrEz30aAtQVXWCBI9VHBjgzOf19QPo,8521
|
|
776
|
+
sglang/srt/managers/scheduler_update_weights_mixin.py,sha256=AuOKrV943inXe5s4cPb4_BQiNAFwkiQGlpaBS-aal-M,6957
|
|
742
777
|
sglang/srt/managers/session_controller.py,sha256=FGADRGSkRmS76o_BQ2fivpgw0Q5Q-K0Ws3aezH41YSc,6041
|
|
743
778
|
sglang/srt/managers/template_manager.py,sha256=M4EshVv1OhKxUAGQPP4OntRkSkUVvG93457xsYfWnQk,11968
|
|
744
|
-
sglang/srt/managers/tokenizer_communicator_mixin.py,sha256=
|
|
745
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
|
746
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
|
747
|
-
sglang/srt/managers/
|
|
748
|
-
sglang/srt/
|
|
749
|
-
sglang/srt/mem_cache/
|
|
750
|
-
sglang/srt/mem_cache/
|
|
751
|
-
sglang/srt/mem_cache/
|
|
752
|
-
sglang/srt/mem_cache/
|
|
753
|
-
sglang/srt/mem_cache/evict_policy.py,sha256=
|
|
779
|
+
sglang/srt/managers/tokenizer_communicator_mixin.py,sha256=CHry04ONVx3YMGNN5KtNJFaafxnw4LfXHceMR1q2Nwc,26088
|
|
780
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=RcK-EvZJj1iNDlhD0WPK7FxxM1cAfKlidnZeJUkpSJ8,90837
|
|
781
|
+
sglang/srt/managers/tp_worker.py,sha256=qENe8zAagoTs50RJmCJi2il9JsQtuQqBHII6XBBPLJg,16212
|
|
782
|
+
sglang/srt/managers/utils.py,sha256=HRPecRiWLHTX6QbkyYRY-tjlpJEb9N1k0fSJsqBxJl8,7324
|
|
783
|
+
sglang/srt/mem_cache/allocator.py,sha256=TEAkK32vyYz7wow5bpZLlrzb3KHVXtw9h1KtGWg6kIo,18246
|
|
784
|
+
sglang/srt/mem_cache/allocator_ascend.py,sha256=GVI1HbNQRy_rIlUHEn-6oRe2WS_OBXfqmoco2Hxta_w,5017
|
|
785
|
+
sglang/srt/mem_cache/base_prefix_cache.py,sha256=Z6c9YKJjInVxvZAZpIh8KRAPlOyE0-aowncm4JMXE70,2813
|
|
786
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=u4EIGuWNonVoCItF2wrKnXzh2OtoDM04XhoffEK6ykE,3923
|
|
787
|
+
sglang/srt/mem_cache/common.py,sha256=PEFKzoawIIPRVboyInPKWG56qht-inp34vcj6q_fsfg,16283
|
|
788
|
+
sglang/srt/mem_cache/evict_policy.py,sha256=FVI4QsFJoRR1CaxE9jpX4OzBPt4w9ftfM2Ndu4BSfhA,1012
|
|
754
789
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
|
755
|
-
sglang/srt/mem_cache/hicache_storage.py,sha256=
|
|
756
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
|
757
|
-
sglang/srt/mem_cache/
|
|
758
|
-
sglang/srt/mem_cache/
|
|
759
|
-
sglang/srt/mem_cache/
|
|
760
|
-
sglang/srt/mem_cache/
|
|
761
|
-
sglang/srt/mem_cache/
|
|
762
|
-
sglang/srt/mem_cache/
|
|
790
|
+
sglang/srt/mem_cache/hicache_storage.py,sha256=t1Dl7OLamm4sPa93sKNIIjSHtX1Rom3D8G9n9GXTipw,8073
|
|
791
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=BK52hyQjPoXKzn_PDn_LRk_3a0AjWBie1Xk4yAO1B3s,35984
|
|
792
|
+
sglang/srt/mem_cache/mamba_radix_cache.py,sha256=mpKTxCzA1_u4eoHk0SvXPPNVVG_JivEAb44miY3aNuw,38678
|
|
793
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=6zpF492cuG4sEXTC41liHi5wSN_dQnDt3sLulRDOPQA,64880
|
|
794
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=IBUKHCmU_Fu8d22_V5ssYp4Ff97w3EaMSpyFZvPD0Go,27634
|
|
795
|
+
sglang/srt/mem_cache/multimodal_cache.py,sha256=23d34nWEDtgiOM6fqAhmkQ8-OHnrNR1-n8Ert0K0n3U,2147
|
|
796
|
+
sglang/srt/mem_cache/radix_cache.py,sha256=7NQHMUKjdKaAGMFdx1z0pCPBPvwux9KcqymFRxFUAY4,28181
|
|
797
|
+
sglang/srt/mem_cache/radix_cache_cpp.py,sha256=PIJenIaR_ouY-pAmyYuI84KY0tDaLg6VAPvKBaNttPM,9663
|
|
798
|
+
sglang/srt/mem_cache/swa_radix_cache.py,sha256=xYK1K6tgyUErhWvfTDfm_TWDRiAWbRNWM1Wd4LSzv4Q,43420
|
|
763
799
|
sglang/srt/mem_cache/cpp_radix_tree/radix_tree.py,sha256=tQZpz-H6HxNAQe9mYqt6aX8mfDZyu_fbJTcCNK-Ns1M,7179
|
|
764
800
|
sglang/srt/mem_cache/storage/__init__.py,sha256=HDzHFUVeOHlry7HlfL5tRd5HUA02N94p8uzA_Va8nlM,251
|
|
765
|
-
sglang/srt/mem_cache/storage/backend_factory.py,sha256=
|
|
766
|
-
sglang/srt/mem_cache/storage/aibrix_kvcache/aibrix_kvcache_storage.py,sha256=
|
|
767
|
-
sglang/srt/mem_cache/storage/aibrix_kvcache/unit_test.py,sha256=
|
|
768
|
-
sglang/srt/mem_cache/storage/eic/eic_storage.py,sha256=
|
|
801
|
+
sglang/srt/mem_cache/storage/backend_factory.py,sha256=ItY0f0YY7fto-oW_yuRxE7lxsv0e6Y3qnWCjgtr2BWE,7859
|
|
802
|
+
sglang/srt/mem_cache/storage/aibrix_kvcache/aibrix_kvcache_storage.py,sha256=0n8jH9Rrcv73X-qcQnaM4ozkb35UMWdxkmeBGfl-O1A,5573
|
|
803
|
+
sglang/srt/mem_cache/storage/aibrix_kvcache/unit_test.py,sha256=asSKZdmlPYxrEzQOqsscfx7fpzV8ueqYwO0npE20otk,3420
|
|
804
|
+
sglang/srt/mem_cache/storage/eic/eic_storage.py,sha256=UVPr5gMfm8TxaxRY2eYf9CsB8JM9VKVO6pI6MrpCvH8,28534
|
|
769
805
|
sglang/srt/mem_cache/storage/eic/test_unit.py,sha256=PfNPpL624t23tyVgtmS5F1pGiuWDMrC39ZD6ZbkN828,3607
|
|
770
|
-
sglang/srt/mem_cache/storage/hf3fs/hf3fs_client.py,sha256=
|
|
806
|
+
sglang/srt/mem_cache/storage/hf3fs/hf3fs_client.py,sha256=3xG0dV5JmnbIJ8kB1_lk8jAeqshOcU7tXES27ldyb8I,5228
|
|
771
807
|
sglang/srt/mem_cache/storage/hf3fs/hf3fs_usrbio_client.py,sha256=6oH4v_WF_pKH4FMSr252v6QPhBCnRHztHqzuS8j6_QI,5323
|
|
772
808
|
sglang/srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp,sha256=dDYPtxmL6OFhEyv_GuTgzkTDpBjcD0EK8kphnn7eaGc,1133
|
|
773
809
|
sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py,sha256=lJ9Jp2kOgQQaUihxlO9l-W8fYfOMa1h1y0WAtzzFGLM,17850
|
|
774
|
-
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=
|
|
810
|
+
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=MI-x2979lvJL8d4aJluTCx6DofIe0tkLTNbrAJbV0FI,21514
|
|
775
811
|
sglang/srt/mem_cache/storage/hf3fs/test_hf3fs_utils.py,sha256=g2h0Woa2CK39pRTigHCVR_hq095dTaC70lCIAIs9THM,1089
|
|
776
|
-
sglang/srt/mem_cache/storage/lmcache/lmc_radix_cache.py,sha256=
|
|
812
|
+
sglang/srt/mem_cache/storage/lmcache/lmc_radix_cache.py,sha256=pd5NC37FORcF-yHmOjbARZGGPcpc-Xd3iu3KGjgYnc4,10009
|
|
777
813
|
sglang/srt/mem_cache/storage/lmcache/unit_test.py,sha256=DCSZDMJAe-HehL9hWzsP759pck36Q-8ijxWZKfgXmA8,3590
|
|
778
|
-
sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py,sha256=
|
|
814
|
+
sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py,sha256=j4KVka-45-RaTnBoGLS8BQnGTxnTLPDOaT-jrFriPKg,20216
|
|
779
815
|
sglang/srt/mem_cache/storage/mooncake_store/test_mooncake_store.py,sha256=6TiqbzEIL71DC7wL1B-Q-SMMZRYsz08sg-dZYeMzmAc,4930
|
|
780
|
-
sglang/srt/mem_cache/storage/nixl/hicache_nixl.py,sha256=
|
|
781
|
-
sglang/srt/mem_cache/storage/nixl/nixl_utils.py,sha256=
|
|
782
|
-
sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py,sha256=
|
|
783
|
-
sglang/srt/metrics/collector.py,sha256=
|
|
784
|
-
sglang/srt/metrics/func_timer.py,sha256=
|
|
816
|
+
sglang/srt/mem_cache/storage/nixl/hicache_nixl.py,sha256=kfGOqJPtq_kiLO2m_bDMFGID9iO79D8iBWadPIgsanY,10911
|
|
817
|
+
sglang/srt/mem_cache/storage/nixl/nixl_utils.py,sha256=3ouXVNJ17nilYF5gKDqphWux2sHqdqD5ztusCv4aP9w,7457
|
|
818
|
+
sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py,sha256=Jj3o2zkPZBBUYzbQeHWV1ujjlC70GYHXmQL_SPStp7Q,10031
|
|
819
|
+
sglang/srt/metrics/collector.py,sha256=Qvwsn5POBDbxsaNRfjwssLszdACtxNeIojq0zfy8O4Q,35327
|
|
820
|
+
sglang/srt/metrics/func_timer.py,sha256=Om9o4svdyPfUpgcwMt6tL560qmbPBQvkDPhPzTwCmvE,3300
|
|
785
821
|
sglang/srt/metrics/startup_func_log_and_timer.py,sha256=PRVg3Z2d5GBMFifZXR-VhzGcn9nmKTkqEU41VJKZmaI,4937
|
|
786
822
|
sglang/srt/metrics/utils.py,sha256=MGb3quRI39n4tgJS1e0UHI5TBX3D0MwsgiZFMW2EsSQ,1903
|
|
787
823
|
sglang/srt/model_executor/cpu_graph_runner.py,sha256=ypp5yIW2OhRX-Xmido5mWuzEFpd-ohlq2c2wEuSW71I,23415
|
|
788
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
|
789
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
|
790
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
|
791
|
-
sglang/srt/model_executor/npu_graph_runner.py,sha256=
|
|
792
|
-
sglang/srt/
|
|
793
|
-
sglang/srt/model_loader/
|
|
824
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=hz7y3q5J7e8lnDhDPxiJIGvtGG7Ws0Og8ztbaZ_mqXw,35580
|
|
825
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=9SsVdDZfGIF-HFm3ulEACjhj95tHQhCzVfe3vzUqZV4,42612
|
|
826
|
+
sglang/srt/model_executor/model_runner.py,sha256=ocjmkK3yKz_z_EAd6sgOZ8xd8qzmpw9f8G1004Ew-L4,100592
|
|
827
|
+
sglang/srt/model_executor/npu_graph_runner.py,sha256=B1YQla4jW9PiciBBisKg-qoC-vmnldRr8ut_aSmUB-E,3664
|
|
828
|
+
sglang/srt/model_executor/piecewise_cuda_graph_runner.py,sha256=-Kb1XILyAxRTbHgT2SzV_BLW-L161eg7vgPiOF1Wrpw,21992
|
|
829
|
+
sglang/srt/model_loader/__init__.py,sha256=Y4gehllriF0JNjly4rGhQPSkUrA9u9Lr-WbfZfBIs6k,1034
|
|
830
|
+
sglang/srt/model_loader/loader.py,sha256=73Pd71im3E56u9SCZmrMgeq5ZJxadeb-ENIIQW4LW9I,80809
|
|
794
831
|
sglang/srt/model_loader/remote_instance_weight_loader_utils.py,sha256=_HnQD1Ab-Wv9oATOmwJe6aQaQD_Gs_yG9EsDCGJQWfs,2881
|
|
795
|
-
sglang/srt/model_loader/utils.py,sha256=
|
|
796
|
-
sglang/srt/model_loader/weight_utils.py,sha256=
|
|
797
|
-
sglang/srt/models/apertus.py,sha256=
|
|
798
|
-
sglang/srt/models/arcee.py,sha256=
|
|
832
|
+
sglang/srt/model_loader/utils.py,sha256=cfMXqVGRppD7CglcFqdMzwhCeB__FHWovYN0IBqkMuw,5001
|
|
833
|
+
sglang/srt/model_loader/weight_utils.py,sha256=O8cdxYdEjMyXgZT0Jz0PdagQGnIgPwnSvAWsyovOHsA,45019
|
|
834
|
+
sglang/srt/models/apertus.py,sha256=Wuz4H8EQUMlqlcCTM3Fe7E0lE0eodb-cX9us1avQxwI,25937
|
|
835
|
+
sglang/srt/models/arcee.py,sha256=O5yGtgAeIdcmYwZNLURWVE6Hu1O0k34gNiUEtux8ozU,18966
|
|
799
836
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
|
800
|
-
sglang/srt/models/bailing_moe.py,sha256=
|
|
801
|
-
sglang/srt/models/bailing_moe_nextn.py,sha256=
|
|
802
|
-
sglang/srt/models/bert.py,sha256=
|
|
837
|
+
sglang/srt/models/bailing_moe.py,sha256=Av6psy73-ZzsHnYLI4OTFshDVvjWtitGn_KQ_CY0fjQ,36313
|
|
838
|
+
sglang/srt/models/bailing_moe_nextn.py,sha256=rzHElrOiXJTV90khQUdx74u4RTXXu07_JUIY_zTRbaw,5930
|
|
839
|
+
sglang/srt/models/bert.py,sha256=2aUAVMT-43VGIbrI8keRBZZdCMOi5PzssykHO00zT94,15791
|
|
803
840
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
|
804
841
|
sglang/srt/models/clip.py,sha256=kOPSXnmgH_QKu2-ENn49HLDS9yf7Gm1HCOE_YvoNhlA,19858
|
|
805
842
|
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
|
806
843
|
sglang/srt/models/dbrx.py,sha256=117gwrB_o8VlACwDH5YlXkPfuS7t2Mh-nyJvpNpIYxs,15903
|
|
807
844
|
sglang/srt/models/deepseek.py,sha256=M7nyHcAbTIs8vc1g6u00oy22-pp704Xp4T3clBzu4xM,17460
|
|
808
845
|
sglang/srt/models/deepseek_janus_pro.py,sha256=td8xGs6ARfJ8AQCYwUhMOZoWigrAs7m3trF5-kXCqik,70418
|
|
809
|
-
sglang/srt/models/deepseek_nextn.py,sha256=
|
|
810
|
-
sglang/srt/models/
|
|
846
|
+
sglang/srt/models/deepseek_nextn.py,sha256=B-Xk9mh7op-Gx42yJKV353yzWzL68iwwR08r6jbNZ6A,6710
|
|
847
|
+
sglang/srt/models/deepseek_ocr.py,sha256=WAPLXeg3S1UB3x3iP-tiandHk5AEnCUMeMs0ak302Gg,52416
|
|
848
|
+
sglang/srt/models/deepseek_v2.py,sha256=EzPUoRGCcBoJIbZ9s_XztIVikp7FSNsTv42qUBzHoNQ,139536
|
|
811
849
|
sglang/srt/models/deepseek_vl2.py,sha256=7X3gI4DE7guUtNJvMLf06jO8MUHKa2Aan8evZg5hsXc,13061
|
|
812
|
-
sglang/srt/models/dots_ocr.py,sha256=
|
|
813
|
-
sglang/srt/models/dots_vlm.py,sha256=
|
|
814
|
-
sglang/srt/models/dots_vlm_vit.py,sha256=
|
|
850
|
+
sglang/srt/models/dots_ocr.py,sha256=sWkFsENjX5b_CecLCqXjepsr6iyyCbNTmjZbRfoB4ek,6683
|
|
851
|
+
sglang/srt/models/dots_vlm.py,sha256=3uLSXO7W8UPKU7a3ixkC_gwSVDGYecCHK0kZAoD6vNs,7192
|
|
852
|
+
sglang/srt/models/dots_vlm_vit.py,sha256=JhX2E0UmjhdelDvR46-_ns5GCYsfnEpeqyDb9NNKUh4,12058
|
|
815
853
|
sglang/srt/models/ernie4.py,sha256=3z14KFdYLR8J-zsm9oO1uBUeLlWrlkHoFKEYvKKJLKM,16079
|
|
816
854
|
sglang/srt/models/ernie4_eagle.py,sha256=E7f-ygCcY8pIoyTMKFyVC2uRcG59-_RaQTO4gd5_uWI,7223
|
|
817
855
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
|
818
|
-
sglang/srt/models/falcon_h1.py,sha256=
|
|
856
|
+
sglang/srt/models/falcon_h1.py,sha256=UQZ8454btjoZ1kbktaqtIjHY1xdvaUZ1ZRnZZ2APlg4,20759
|
|
819
857
|
sglang/srt/models/gemma.py,sha256=2atKwFN5wCsJCmBRmURX9vaCcFjxlFirL7xsnG5KPlI,14180
|
|
820
858
|
sglang/srt/models/gemma2.py,sha256=n2s3WLGVM3XDvOXwbi_h7tgeh5SDDv1VvifH680DmV0,16785
|
|
821
859
|
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
|
822
860
|
sglang/srt/models/gemma3_causal.py,sha256=o46BNbaiOeoOv2xVU6-lWZhrrjyGskdebve0_wviWfU,27338
|
|
823
|
-
sglang/srt/models/gemma3_mm.py,sha256=
|
|
861
|
+
sglang/srt/models/gemma3_mm.py,sha256=9JpkNj_u-8Af9RJJQbUNGOxWmvW3TbXUceoI6omb8jc,18030
|
|
824
862
|
sglang/srt/models/gemma3n_audio.py,sha256=isgKfjA5UieYawxU6medL2ssXlzYPqAbagDBnLcemC0,36405
|
|
825
863
|
sglang/srt/models/gemma3n_causal.py,sha256=kBDlpSWAg6ZDmUPe08Q7sj5CbdVD_0h07zwJw8sKu7I,36335
|
|
826
|
-
sglang/srt/models/gemma3n_mm.py,sha256=
|
|
864
|
+
sglang/srt/models/gemma3n_mm.py,sha256=Il5LHjZdbHEXueUVdBp5lpSJHt56W7fpfPHD0Y7RED4,20301
|
|
827
865
|
sglang/srt/models/glm4.py,sha256=dijzVTTgg8zyJ3gga95MKY0WwqwnuAaf-VIV93OFAmc,11433
|
|
828
|
-
sglang/srt/models/glm4_moe.py,sha256=
|
|
829
|
-
sglang/srt/models/glm4_moe_nextn.py,sha256=
|
|
830
|
-
sglang/srt/models/glm4v.py,sha256=
|
|
831
|
-
sglang/srt/models/glm4v_moe.py,sha256=
|
|
866
|
+
sglang/srt/models/glm4_moe.py,sha256=plEh-b5C2az6MMNF5hotXIusJAEdXOZy7KTRd4EIRLg,41209
|
|
867
|
+
sglang/srt/models/glm4_moe_nextn.py,sha256=fWuDWY8nwnHBXpdEYkhyMcBkUByIrBZvEMdLEtsTVi8,5947
|
|
868
|
+
sglang/srt/models/glm4v.py,sha256=LwiFQxYm2ksmaePeO57i5d4YGQjiQX52e-Dsjyh_P7I,23834
|
|
869
|
+
sglang/srt/models/glm4v_moe.py,sha256=MxuF0pFf2frKPCp4A_2YmrXx_uvZzOFdA4hVJFbLY6E,17375
|
|
832
870
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
|
833
871
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
|
834
|
-
sglang/srt/models/gpt_oss.py,sha256=
|
|
872
|
+
sglang/srt/models/gpt_oss.py,sha256=K9g2c9xTE2eM74isijM-KSvGPHt6Cjgjl8L8EzBTLmM,43711
|
|
835
873
|
sglang/srt/models/granite.py,sha256=8q92shxVPAp_cJDohJATffSGd7Z0Oi-vF5jpY6DlK4s,19840
|
|
836
874
|
sglang/srt/models/granitemoe.py,sha256=j1rgZ62CbBioECjUblDCw_NneDQgY_QJODsI0fqXVO8,13779
|
|
837
|
-
sglang/srt/models/grok.py,sha256=
|
|
838
|
-
sglang/srt/models/hunyuan.py,sha256=
|
|
875
|
+
sglang/srt/models/grok.py,sha256=qEuuoVg5aaVGPyjuYvx_rTRcAiUToDNv0IQ8XbCXOr4,40021
|
|
876
|
+
sglang/srt/models/hunyuan.py,sha256=i4RUEDDwvflGV6hciBjTS46G10ew0DJcmaUpONkxlF4,30950
|
|
839
877
|
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
|
840
878
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
|
841
879
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
|
842
|
-
sglang/srt/models/interns1.py,sha256=
|
|
880
|
+
sglang/srt/models/interns1.py,sha256=VZAGsvjkjPhdUvvLuSy9qV40KXsBTy0KdiXg00EeOnE,12450
|
|
843
881
|
sglang/srt/models/internvl.py,sha256=iQm2wDtkcyjPYoV9oY_jQ3_7WvhP315eP_vZEiQX3uw,27062
|
|
844
|
-
sglang/srt/models/kimi_vl.py,sha256=
|
|
845
|
-
sglang/srt/models/kimi_vl_moonvit.py,sha256=
|
|
846
|
-
sglang/srt/models/llama.py,sha256=
|
|
882
|
+
sglang/srt/models/kimi_vl.py,sha256=Tm0-cZXzD3FNW6YEoAFGqCX7ExW4hni-RGFsK3GOCcg,12707
|
|
883
|
+
sglang/srt/models/kimi_vl_moonvit.py,sha256=qtS8ANHYJ_VPrnzg7oSN30nGAnxfn6LA7xQ8GPH9uQM,23939
|
|
884
|
+
sglang/srt/models/llama.py,sha256=Et_i6a1A3TL0pS6ccD8NIOiBpqTxjmSMl1KUQsAXotE,28248
|
|
847
885
|
sglang/srt/models/llama4.py,sha256=i4-Vo5FVE9zf_6Y80dyft5VjPOQ-a-xWYfEV8s-ltKQ,19872
|
|
848
886
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
|
849
887
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
|
850
|
-
sglang/srt/models/llama_eagle3.py,sha256=
|
|
888
|
+
sglang/srt/models/llama_eagle3.py,sha256=yezjnua5fBjTwJT2lKmybn0uAE7dKOJtazN2fWxqY_k,9182
|
|
851
889
|
sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OWYfirZnA,3254
|
|
852
890
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
|
853
891
|
sglang/srt/models/llava.py,sha256=xzYip_BAwpzSIdZre43LZiyTpFISa0ZCLdO6LUSbaCg,37702
|
|
854
892
|
sglang/srt/models/llavavid.py,sha256=-CSk0RJ2MQeb81sh-RISeVJFaI-XWY6nR6_I594MkME,12818
|
|
855
|
-
sglang/srt/models/longcat_flash.py,sha256=
|
|
856
|
-
sglang/srt/models/longcat_flash_nextn.py,sha256=
|
|
857
|
-
sglang/srt/models/mimo.py,sha256=
|
|
858
|
-
sglang/srt/models/mimo_mtp.py,sha256=
|
|
893
|
+
sglang/srt/models/longcat_flash.py,sha256=CjlGMrV5IYZ98DoCByiN61rVn2CFtVKEEH7oWNp0OwY,40507
|
|
894
|
+
sglang/srt/models/longcat_flash_nextn.py,sha256=tbM7UYNs8iP_N2SN3tgP1GA3S9oEEq9KDkVPV-DF4hY,29353
|
|
895
|
+
sglang/srt/models/mimo.py,sha256=TdiflXteo_HLH7Q1Yf6xDAOXRzNrOpLR4kjVXMueltM,5662
|
|
896
|
+
sglang/srt/models/mimo_mtp.py,sha256=HbdSi0ZXW30YfQYhubnU6JmUI0zceJLvRjI2ptmqbVw,7251
|
|
859
897
|
sglang/srt/models/minicpm.py,sha256=CzBJyZtfMpp8jvlEl29DHI7HLVq-CxuqP1UHwxIbaUI,14567
|
|
860
898
|
sglang/srt/models/minicpm3.py,sha256=Cflu4Tb2hxpjapRBZ5n4kX8a1nnFwffK-M8uHPRUra4,19276
|
|
861
|
-
sglang/srt/models/minicpmo.py,sha256=
|
|
899
|
+
sglang/srt/models/minicpmo.py,sha256=1bNtbJM5wbMjV4ax8gesVsYVbMz4ozaIHAvvi8_d0iE,76175
|
|
862
900
|
sglang/srt/models/minicpmv.py,sha256=_CnCR2y3RaYxhONAKFpBIuPQBrqn9Od4o7QnJw8CLR4,35884
|
|
863
901
|
sglang/srt/models/mistral.py,sha256=ni7PppA_5X4ivTnIps3yoEaMEL-G6Gaf9b5hGC1vU5Q,3475
|
|
864
|
-
sglang/srt/models/mixtral.py,sha256=
|
|
902
|
+
sglang/srt/models/mixtral.py,sha256=bZdsTw4A3B-MIHSR8U26mBv3sLYkawVM4V1VXEyBrmE,16992
|
|
865
903
|
sglang/srt/models/mixtral_quant.py,sha256=UUIq7lpUonD9IoGePyl59oJYEcVwT9wUXvtVp5tjQ9Y,15406
|
|
866
|
-
sglang/srt/models/mllama.py,sha256=
|
|
867
|
-
sglang/srt/models/mllama4.py,sha256=
|
|
904
|
+
sglang/srt/models/mllama.py,sha256=mMhDrLd1jJ-4lwMMHKRC5Uzcs3kWdzRJJzdjhQN4LOw,39671
|
|
905
|
+
sglang/srt/models/mllama4.py,sha256=z6YKfmHu0lJ-oyALZNlL9-EcHzFvNgkxWU_mURyS7z4,36694
|
|
906
|
+
sglang/srt/models/nemotron_h.py,sha256=clbTirOxve6yefRaf2eE0dT0IqhPDfknOtnsAEsnZOM,17904
|
|
868
907
|
sglang/srt/models/nemotron_nas.py,sha256=CoSAKqlbej4Xe30uY4w76iASBqeuJf8-imisDK00zEU,15964
|
|
869
908
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
|
870
|
-
sglang/srt/models/olmo2.py,sha256=
|
|
909
|
+
sglang/srt/models/olmo2.py,sha256=zprucQEogxPV38E_IU0edcTYP-d-dqLVeTmt2kRLznA,15448
|
|
871
910
|
sglang/srt/models/olmoe.py,sha256=zryYUQEhEdhd6xcR_HyLV7gHCcKt-HWHeEeIUqmhmcc,16100
|
|
872
|
-
sglang/srt/models/opt.py,sha256
|
|
911
|
+
sglang/srt/models/opt.py,sha256=-nCg_g2I84JtJQ7Fhh2eyp1cko3TxxicheM7gGpX0A0,23415
|
|
873
912
|
sglang/srt/models/persimmon.py,sha256=86Duo3HiZqDj9O2UzWbJgUEhQOXzGBUdhUofQhcs1VE,11244
|
|
874
|
-
sglang/srt/models/phi.py,sha256=
|
|
913
|
+
sglang/srt/models/phi.py,sha256=tnhdiD_zo7KeHMTI8UxDfJN5brpHSAaKPSN-2e2iGk0,10280
|
|
875
914
|
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
|
876
|
-
sglang/srt/models/phi4mm.py,sha256=
|
|
915
|
+
sglang/srt/models/phi4mm.py,sha256=Pe5IjZcu7N8w_UmEXO0Mb98-tihc50ih6y5cS7b6BIY,20597
|
|
877
916
|
sglang/srt/models/phi4mm_audio.py,sha256=0ChekwoYudAnbY0-JyNwz_inzMlxM8FmULqR9mwkPhQ,48877
|
|
878
917
|
sglang/srt/models/phi4mm_utils.py,sha256=bW3un4x3SHDvSkAOHQEFO286FGdOPeKhBpJCOmNlC9E,66956
|
|
879
|
-
sglang/srt/models/phimoe.py,sha256=
|
|
880
|
-
sglang/srt/models/pixtral.py,sha256=
|
|
881
|
-
sglang/srt/models/
|
|
918
|
+
sglang/srt/models/phimoe.py,sha256=cZQIGjEvArPDiJzC3uKYje-o48QZC699P8TTLwfVIas,19172
|
|
919
|
+
sglang/srt/models/pixtral.py,sha256=H378jvdhwjgdAuUszhCe5tmcEPYvw2YPhg_d8QrjLZE,16776
|
|
920
|
+
sglang/srt/models/points_v15_chat.py,sha256=HV_GRgLTcetKh0B2agJry02N_atcWI5NPjjQELarUGk,6415
|
|
921
|
+
sglang/srt/models/qwen.py,sha256=_X1mUt_MczEE2jFK7rfGyRRtpd4U93jdD1SVpCTNsns,11856
|
|
882
922
|
sglang/srt/models/qwen2.py,sha256=kHNZCtT0jnQXC2aJN7Bp1DzaEzKWuhUAGL3hAmt8OU8,23598
|
|
883
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
|
884
|
-
sglang/srt/models/qwen2_audio.py,sha256=
|
|
923
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=X7Hh-75gsoGqaK2iJg7eBUFR_8qwJRLhhkii3yxc-KA,25084
|
|
924
|
+
sglang/srt/models/qwen2_audio.py,sha256=Hr4j9W-q23XjQUX4kk1NxUGA-EQkj8AKDqKVK741TjI,7097
|
|
885
925
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
|
886
926
|
sglang/srt/models/qwen2_eagle.py,sha256=6spFg6JYQGeUXLv2Q5eMkVzZvnqGyvW6SdVBtFMxlTM,4806
|
|
887
|
-
sglang/srt/models/qwen2_moe.py,sha256
|
|
927
|
+
sglang/srt/models/qwen2_moe.py,sha256=-pkURmqiLazr7oq11-3hQCFKrdj1crx30Z7iK7DBs90,30920
|
|
888
928
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
|
889
|
-
sglang/srt/models/qwen2_vl.py,sha256=
|
|
929
|
+
sglang/srt/models/qwen2_vl.py,sha256=xV8s6kgyjZ37SqLi9nF9J6n3gq9piUmlXOe2PVPQqjI,21488
|
|
890
930
|
sglang/srt/models/qwen3.py,sha256=2OSKkk-AdIpg6ZnNcQ9tqZLlF-VH-QxncY1J_g8k-bc,19637
|
|
891
931
|
sglang/srt/models/qwen3_classification.py,sha256=bdjAylXJCjXKjAho74nmtIMpEG0Af98N-aZQ-pKKMY0,3262
|
|
892
|
-
sglang/srt/models/qwen3_moe.py,sha256=
|
|
893
|
-
sglang/srt/models/qwen3_next.py,sha256=
|
|
894
|
-
sglang/srt/models/qwen3_next_mtp.py,sha256=
|
|
895
|
-
sglang/srt/models/
|
|
896
|
-
sglang/srt/models/
|
|
932
|
+
sglang/srt/models/qwen3_moe.py,sha256=W27Yaut4mNOutT91D31MxaLfAPXJF9jItTmANkFArCM,33363
|
|
933
|
+
sglang/srt/models/qwen3_next.py,sha256=hbIiLXcPBNa41lRnqZqdXa7Q8FDYX9JlaviXIZN_BEk,37279
|
|
934
|
+
sglang/srt/models/qwen3_next_mtp.py,sha256=nua9MgSa0_2Dz2Zju0chk6VXGDndBqr-1xMQ-_OirTU,4387
|
|
935
|
+
sglang/srt/models/qwen3_omni_moe.py,sha256=X5dB2zB1LAAD6_baK84y6MGvEm5ArgcFDmarUyoaS9c,25444
|
|
936
|
+
sglang/srt/models/qwen3_vl.py,sha256=fNTKorRODMDFOkARN0vcC8sLrcwLZlLpNCf_JQJKohM,29489
|
|
937
|
+
sglang/srt/models/qwen3_vl_moe.py,sha256=rY87FpfVOpHw0PuYu7l5nt3sFdSIHrn964XLVQjLyLY,13708
|
|
897
938
|
sglang/srt/models/registry.py,sha256=BpYy-E2m5jPmCNmue_o3G9lCQza1ge7ftmTJQ78pFGc,4276
|
|
898
|
-
sglang/srt/models/roberta.py,sha256=
|
|
899
|
-
sglang/srt/models/sarashina2_vision.py,sha256=
|
|
939
|
+
sglang/srt/models/roberta.py,sha256=h5lLKiLIjBxYEFgUORWXWdW6bJ8skKyFWNnEqVJXBt4,11907
|
|
940
|
+
sglang/srt/models/sarashina2_vision.py,sha256=tvH4Zb-U9pgcrxm_7Uurnmr5Xeo0xXcWYHuucIDseks,10913
|
|
900
941
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
|
901
942
|
sglang/srt/models/solar.py,sha256=BM30Eyn5Ptc0PCA6Lx3Hn7LZ_fV05n0rVm0vY_ILv5Y,18347
|
|
902
943
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
|
903
944
|
sglang/srt/models/starcoder2.py,sha256=ts6LDIjQ2FVnyLk4s2K9COD01RRhewJDW-VlvoyAk24,12377
|
|
904
|
-
sglang/srt/models/step3_vl.py,sha256=
|
|
945
|
+
sglang/srt/models/step3_vl.py,sha256=QeU7RQ5YnU6FcAi4c-ICVABpM1PJ5E65w5XE3UJmIbE,35557
|
|
905
946
|
sglang/srt/models/torch_native_llama.py,sha256=3xf6CzCiizJ8i94GIChpOLq9q64Xa519RtuEspPTZQk,18501
|
|
906
947
|
sglang/srt/models/transformers.py,sha256=laA2h39MPeiAWKv4DEg0ydre-1pyXWFSRga-nwy1HUk,10244
|
|
907
|
-
sglang/srt/models/utils.py,sha256=
|
|
948
|
+
sglang/srt/models/utils.py,sha256=yB1rHC9Xk6hTQ59Fy2ExdrtntuSn6vkm-idf3CFrYP4,2032
|
|
908
949
|
sglang/srt/models/vila.py,sha256=3NiRHWOqXnCRjXmswAldsNtiE5zRILbScEsbhUzLZF4,9846
|
|
909
950
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
|
910
951
|
sglang/srt/models/xverse_moe.py,sha256=nBtG_PAK8wcp1tW2l2Zby2oEOmtWAYzH5COH-_N5IAM,17072
|
|
911
952
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
|
912
953
|
sglang/srt/multimodal/mm_utils.py,sha256=6bV1_a7Iet9W0y3qdd0E-hFM78zalIzNZCYbLzJX2y8,12640
|
|
913
|
-
sglang/srt/multimodal/processors/base_processor.py,sha256=
|
|
954
|
+
sglang/srt/multimodal/processors/base_processor.py,sha256=RAJYoUI8XGTa97rJKz72V0UzTMzfpKvU3206GjRJ0ZQ,25053
|
|
914
955
|
sglang/srt/multimodal/processors/clip.py,sha256=5nXZuQYbyf-5mlqPwjhQrlWqxvswImWZQXivChsiHfQ,1057
|
|
915
|
-
sglang/srt/multimodal/processors/
|
|
916
|
-
sglang/srt/multimodal/processors/
|
|
956
|
+
sglang/srt/multimodal/processors/deepseek_ocr.py,sha256=ZuP-zHNjPV3-lb6NkmNIitwIiXtNopNIwOLPttLjBYI,1234
|
|
957
|
+
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=nKqWQ9PmtY66cMx0YhIHGPaGIW-VyPKt_KeRqFLU60c,2479
|
|
958
|
+
sglang/srt/multimodal/processors/dots_vlm.py,sha256=azazFc_lFj40NJKWf1X1MGgJ5FXgv2RlgVS-R6IhFdk,3521
|
|
917
959
|
sglang/srt/multimodal/processors/gemma3.py,sha256=7aD6cR60iSC_MqjzdCDMAgtrb_cmy9YJyqLgVRClBT8,1986
|
|
918
960
|
sglang/srt/multimodal/processors/gemma3n.py,sha256=mtmvBasOMxb3Y2NLZR02nMYX30RLUXhDYJ5uVOElr10,2776
|
|
919
|
-
sglang/srt/multimodal/processors/glm4v.py,sha256=
|
|
920
|
-
sglang/srt/multimodal/processors/internvl.py,sha256=
|
|
921
|
-
sglang/srt/multimodal/processors/janus_pro.py,sha256=
|
|
961
|
+
sglang/srt/multimodal/processors/glm4v.py,sha256=EPPILSirXexpRkWZfIhxWGgWKZGk1q6eENZS5gWyfjw,4899
|
|
962
|
+
sglang/srt/multimodal/processors/internvl.py,sha256=vvOlWmJ4AzbXnDxHED1NkRgHQfOnZlmEaWMA3-1_2cQ,9765
|
|
963
|
+
sglang/srt/multimodal/processors/janus_pro.py,sha256=nd1v0--5733pOwWTpArnOHCfh4aHHVBUOJPOhk9rLd4,1395
|
|
922
964
|
sglang/srt/multimodal/processors/kimi_vl.py,sha256=5i8KmGxnnDtQc7XqUBNyanAfGxhxj8iRFBFONHmpiFg,1565
|
|
923
965
|
sglang/srt/multimodal/processors/llava.py,sha256=-YtDc_7TsMWmwKkD4KJZW2Y0jPFlZtbQ38K_N24hk0w,8231
|
|
924
966
|
sglang/srt/multimodal/processors/minicpm.py,sha256=ysJlUaxcBcWjKliz5VmXKVv0ec4QWRHXZk4ga-hXVf0,5354
|
|
925
967
|
sglang/srt/multimodal/processors/mlama.py,sha256=FgPm2JQzfPFDcGYDm0mqfDfO_eJKy-NiVgF-vId6w8Y,1233
|
|
926
|
-
sglang/srt/multimodal/processors/mllama4.py,sha256=
|
|
927
|
-
sglang/srt/multimodal/processors/phi4mm.py,sha256=
|
|
968
|
+
sglang/srt/multimodal/processors/mllama4.py,sha256=pYzqbuV9Hb5RMYNLRabTMIMTwL8C5SCToZdhSg403go,1653
|
|
969
|
+
sglang/srt/multimodal/processors/phi4mm.py,sha256=8Co-UPT8Am2P5dfW8bjZcy-pVAPqFXW7hbK8v23NMiA,3781
|
|
928
970
|
sglang/srt/multimodal/processors/pixtral.py,sha256=Lx5Z-9NkovLDTHlRBznHxGn4r2XhDz8am2XpOskOVQY,3203
|
|
971
|
+
sglang/srt/multimodal/processors/points_v15_chat.py,sha256=n1lwAnAYk1xPhnZRpAtDDpyP8N7NlZGwX7Pdun9Kv50,1581
|
|
929
972
|
sglang/srt/multimodal/processors/qwen_audio.py,sha256=xkIFrHepF8Ok6MB-1OwVz1BmzPmEPgUe8lIb0azO2Bc,2411
|
|
930
|
-
sglang/srt/multimodal/processors/qwen_vl.py,sha256=
|
|
973
|
+
sglang/srt/multimodal/processors/qwen_vl.py,sha256=h26WSDFJiXvyCmUxNwetjgDANxXoQGxocdd_uudC2Vw,13537
|
|
931
974
|
sglang/srt/multimodal/processors/sarashina2_vision.py,sha256=E0KSOw_yzc7prHkQfMHS_DzOcYL1GZJ77NopVkd_V5M,3024
|
|
932
|
-
sglang/srt/multimodal/processors/step3_vl.py,sha256=
|
|
975
|
+
sglang/srt/multimodal/processors/step3_vl.py,sha256=2zNf1gT-fSrA88-cvkr6xJDE0sEWFKdBDUWsMiFx_uY,18330
|
|
933
976
|
sglang/srt/multimodal/processors/vila.py,sha256=vWgV1lTdjiFiTR8w-7fC66-L_tpOOD59c-c9NljGelE,2192
|
|
934
977
|
sglang/srt/parser/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
|
935
|
-
sglang/srt/parser/conversation.py,sha256=
|
|
978
|
+
sglang/srt/parser/conversation.py,sha256=r5Fp4BGNjGeuvBw7dAUt-aUl3ExsTSG00Gq8dS8_hj0,40089
|
|
936
979
|
sglang/srt/parser/harmony_parser.py,sha256=YweG4azWm5jmzYGaAHEXSaORpgWctPpSGQk_jp5H-CE,23227
|
|
937
980
|
sglang/srt/parser/jinja_template_utils.py,sha256=_rtLpriMmodo-tBD8B9ifu3BsZFdaQQCDPRUqF26pIg,8006
|
|
938
|
-
sglang/srt/parser/reasoning_parser.py,sha256=
|
|
939
|
-
sglang/srt/sampling/custom_logit_processor.py,sha256=
|
|
940
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
|
941
|
-
sglang/srt/sampling/sampling_params.py,sha256=
|
|
981
|
+
sglang/srt/parser/reasoning_parser.py,sha256=Q5yC-Giug7fA0W5d1BarTKUWWFO5QUwtnonMeuDziOw,11149
|
|
982
|
+
sglang/srt/sampling/custom_logit_processor.py,sha256=phIOI0ttJHQ_yCZhnqD5qNs98QG0gdY9evbXkgS3544,4272
|
|
983
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=xlkEs3zgrwZCNBs69JHL3og9-jJnFbDD3_RLJJ-M36U,15544
|
|
984
|
+
sglang/srt/sampling/sampling_params.py,sha256=ULhZRhA9C1oK34T3cbwqaODV3iMX8HL1VOlo_gewzZw,9193
|
|
942
985
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
|
943
986
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
|
944
987
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
|
945
988
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=Romk41ahToaVlNMnnd1Enko7_kRA4KdMGO94qnEbDHA,6061
|
|
946
989
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
|
947
|
-
sglang/srt/speculative/
|
|
948
|
-
sglang/srt/speculative/
|
|
949
|
-
sglang/srt/speculative/
|
|
950
|
-
sglang/srt/speculative/
|
|
951
|
-
sglang/srt/speculative/
|
|
952
|
-
sglang/srt/speculative/
|
|
953
|
-
sglang/srt/speculative/
|
|
954
|
-
sglang/srt/speculative/
|
|
955
|
-
sglang/srt/speculative/
|
|
956
|
-
sglang/srt/speculative/
|
|
990
|
+
sglang/srt/speculative/base_spec_worker.py,sha256=M2hIHGmno1ew_gbgsU7rcIsNzR7pixDkN0UDJpZneEY,698
|
|
991
|
+
sglang/srt/speculative/draft_utils.py,sha256=E7u9u_-lrjOu82bBqmLB6zsbygRbWuLHO0Y1NwfbH4o,8261
|
|
992
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=LmqXLmMxLBuAFz8XiJpBQAsjpX77ZLrcDlv2hCXDRKs,14995
|
|
993
|
+
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=AucQHsYM9hktPgmjtygPCxjMyQhFikJX_pc41APXR4M,16737
|
|
994
|
+
sglang/srt/speculative/eagle_info.py,sha256=ucS_hYCxoKlHA8pGtDN5mdk9i6z-NHYq4vAz1uLGcwk,31479
|
|
995
|
+
sglang/srt/speculative/eagle_info_v2.py,sha256=2PmbYzDrMkgNky0xeTIVaL04hDI15JaEqaE8pUlsu8c,16548
|
|
996
|
+
sglang/srt/speculative/eagle_utils.py,sha256=HA_h9dkO9RLOBXn4dFFQHY3yiSw4CwjuYewer5BchHI,4581
|
|
997
|
+
sglang/srt/speculative/eagle_worker.py,sha256=m40xi1IAWZQLX48D297BZy7ohlCWbptqkOszXmWC9JA,39344
|
|
998
|
+
sglang/srt/speculative/eagle_worker_v2.py,sha256=nzW7KQFBwU8F7F4CRlBGr7i_7_uCJzjcdMA5zCHqdB8,26315
|
|
999
|
+
sglang/srt/speculative/ngram_info.py,sha256=WEpR-I6dGbzKPvH915pPysONO5TodtyfrX0mN9LNBMU,16777
|
|
1000
|
+
sglang/srt/speculative/ngram_worker.py,sha256=t05lgkBATs-mo45eloiqvMalsJKdHI7fZ2BTYEpXoxg,9720
|
|
1001
|
+
sglang/srt/speculative/spec_info.py,sha256=1AkkpJwifuOtB1ZEjLctrzzjC46O1qtJIkoAdY2rmas,2669
|
|
1002
|
+
sglang/srt/speculative/spec_utils.py,sha256=hxm84b37ADwntrlpJ6JOxVGdZ22Ek4uBICnHUy82AxU,21345
|
|
1003
|
+
sglang/srt/speculative/standalone_worker.py,sha256=9PfG1-aXG3W4j43vLnSvBuaOqgqs-MsfWRH1e7nbkSg,3745
|
|
957
1004
|
sglang/srt/speculative/cpp_ngram/ngram.cpp,sha256=j8D4xNaa8dv8CN9F5TG_yHxil-A79XiuMjyEE3ZUOSs,12962
|
|
958
1005
|
sglang/srt/speculative/cpp_ngram/ngram.h,sha256=9OMOzO3KXEVbT5gEXjK-IRATI63in54LjeT_Xba5DSU,2492
|
|
959
1006
|
sglang/srt/speculative/cpp_ngram/ngram_cache.py,sha256=Y22AM1CC0zOOarMWJzZQKz1-IMk3d4isSGkk-Uti74I,4383
|
|
960
1007
|
sglang/srt/speculative/cpp_ngram/ngram_cache_binding.cpp,sha256=yrRXulpjivoSveCRL5ORfZ0hj2yXqjdVqc88APUJllg,1911
|
|
961
1008
|
sglang/srt/speculative/cpp_ngram/param.h,sha256=tLSD_Ke1c2GjTY9tl3p1UgpbrBfaZqPRsHfw2YJ87hw,4375
|
|
962
1009
|
sglang/srt/speculative/cpp_ngram/queue.h,sha256=m8OK4Nd6_yWnJkWxx-JRqUIOfzQwi3apy_3TvyxSY4Q,1288
|
|
963
|
-
sglang/srt/tokenizer/tiktoken_tokenizer.py,sha256=
|
|
1010
|
+
sglang/srt/tokenizer/tiktoken_tokenizer.py,sha256=xIi7o38MB-pWPLC6sTdmGC9NN_kgRDvMStIo0nJZulw,6246
|
|
964
1011
|
sglang/srt/tracing/trace.py,sha256=5SKy8XA4KLaTcBO6ZJvJSP_IYK5--2RJN0Q6O6Vg10g,16110
|
|
965
|
-
sglang/srt/utils/__init__.py,sha256=
|
|
966
|
-
sglang/srt/utils/
|
|
967
|
-
sglang/srt/utils/
|
|
1012
|
+
sglang/srt/utils/__init__.py,sha256=zuoHoZnKrciwFy11a6p5Ua8mYU67QUI_09L0SfEjpeo,102
|
|
1013
|
+
sglang/srt/utils/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
|
1014
|
+
sglang/srt/utils/bench_utils.py,sha256=0xXUeDk61RynxbOV0P_okb-5rLPpc-ZqfCGx3W35K4I,4421
|
|
1015
|
+
sglang/srt/utils/common.py,sha256=uSu4JABt4oSwJiLFSaqLgkMkw8QDXn5ydrkslOUXb48,113357
|
|
1016
|
+
sglang/srt/utils/hf_transformers_utils.py,sha256=x5HyF75geb7vskOU9FaHarxK_u2MprUZm1SrmgMQX0E,17696
|
|
1017
|
+
sglang/srt/utils/host_shared_memory.py,sha256=0tO3qMlbmEIs11XvdI7BB0AtH4Z5hm9vWEkEyau4vlM,2264
|
|
1018
|
+
sglang/srt/utils/offloader.py,sha256=mKN1Vd0ftr2mjcVIXKCZnc51pcQ6bfYvhqFvdAUyRC4,18771
|
|
968
1019
|
sglang/srt/utils/patch_torch.py,sha256=yaVs6YNm63rFYBw-v59usYR3cmb_qX6F69L5dMfQCxg,3307
|
|
969
1020
|
sglang/srt/utils/poll_based_barrier.py,sha256=9vjn32ROlSueEk7EuZjWKUrrL7XVR9KJsSVliGTYB_4,937
|
|
1021
|
+
sglang/srt/utils/profile_merger.py,sha256=bvnz-yHMb7zHE1Bv09JKgCgYZY1n4h_UK7Wz2wNAmro,7202
|
|
970
1022
|
sglang/srt/utils/rpd_utils.py,sha256=F8FWL_mT05xKQYLrzCJ8Q_5zfZJ86dHxX6LEqpwC7rw,20743
|
|
971
1023
|
sglang/srt/utils/slow_rank_detector.py,sha256=81-KXp33wevk4jG2QuThsc17fLdmdeMouxwVfSXscic,2052
|
|
1024
|
+
sglang/srt/utils/torch_memory_saver_adapter.py,sha256=WFwPsOBvnWu6N2yTHmiOjLbDAYosslHwNSfyFHjz-7w,2511
|
|
972
1025
|
sglang/srt/weight_sync/tensor_bucket.py,sha256=vp_LRrhULNnxiw9Tf56FcEckgUg07lifgv1lasG6y7o,3695
|
|
973
1026
|
sglang/srt/weight_sync/utils.py,sha256=1FHM5kBav1GJUyYQLKHSJAh9MXwsuizDWxAVJMg1ZgE,4155
|
|
974
1027
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
975
1028
|
sglang/test/doc_patch.py,sha256=P9PYjBIVlZHvP9M34qS-8m1scmDP27ciNJNvZOdrUKE,1614
|
|
976
1029
|
sglang/test/few_shot_gsm8k.py,sha256=zalplyHOYCnIwAnSQg-xlZl-Q-wGuMfjLdl9EJnUN7U,4333
|
|
977
|
-
sglang/test/few_shot_gsm8k_engine.py,sha256=
|
|
1030
|
+
sglang/test/few_shot_gsm8k_engine.py,sha256=Vgs0SBguumrdlGOY1Hjjc8nTIdv5mxiTAmR4Isa4g4I,3793
|
|
978
1031
|
sglang/test/get_logits_ut.py,sha256=XotfHBDbQDRuSrJLRErsrdIOA0WDflnrK9171E-2iWE,1822
|
|
979
|
-
sglang/test/
|
|
980
|
-
sglang/test/
|
|
981
|
-
sglang/test/
|
|
982
|
-
sglang/test/
|
|
983
|
-
sglang/test/
|
|
984
|
-
sglang/test/
|
|
1032
|
+
sglang/test/kit_matched_stop.py,sha256=60YESivdEqn6XXUa9oLu1UeLozp4ahteEEvWyOUVDx8,5382
|
|
1033
|
+
sglang/test/run_eval.py,sha256=88EUq7X9L1jN83IO9kijEoBXq9CS0DHgKaiX4QtgmUk,7829
|
|
1034
|
+
sglang/test/runners.py,sha256=dz4ZlbsF7BePTrS84BmlVt8LnxkoZhkyCPdjGg1hd04,34203
|
|
1035
|
+
sglang/test/send_one.py,sha256=sxdAVh6nxq8IgPf1behPiWF7ZVugwoOE4DjdJyY6qzo,6392
|
|
1036
|
+
sglang/test/simple_eval_common.py,sha256=06wMMTLf8kpbySBtImD9xdjmYCPuJSghhKcJ_D_KdB4,12976
|
|
1037
|
+
sglang/test/simple_eval_gpqa.py,sha256=Ui416_9Fh8TYU_51bClhEXi6wVCLEhLG28a7qPJfJYQ,3276
|
|
1038
|
+
sglang/test/simple_eval_humaneval.py,sha256=AhB-0dimur6_vSH9qHVyCRag_VZ8Jf3gH6PdmTkPHAU,5658
|
|
1039
|
+
sglang/test/simple_eval_longbench_v2.py,sha256=LLa3qAmF8PF1HGC-ubNcaB4jaz22NhZBY67rIzTH5Dk,12169
|
|
985
1040
|
sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWUpk,2550
|
|
986
1041
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
|
987
1042
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
|
988
1043
|
sglang/test/simple_eval_mmmu_vlm.py,sha256=XpADoB825LUX-n4hDFOR3wkuowdLPB6sMHJEvM2dah8,15195
|
|
989
1044
|
sglang/test/test_activation.py,sha256=bDBFl4Y30siXj7Ifl66fc2HytOrcZdHFiP2i9K8TIsY,3140
|
|
990
|
-
sglang/test/test_block_fp8.py,sha256=
|
|
991
|
-
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=
|
|
992
|
-
sglang/test/test_block_fp8_ep.py,sha256=n4X6ZKwuUUbV5Ofjg64ptlaFGI1LbRXDfFiJW1ELHgY,10546
|
|
1045
|
+
sglang/test/test_block_fp8.py,sha256=z7cVJLy9jfD-xer3lALeBWkzRxhseqSboBAw75LZGgE,21828
|
|
1046
|
+
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=G6Yw6npnUO8OSuu4L2fOl-vP3mYCI7Mcrst6hc96t4s,8170
|
|
993
1047
|
sglang/test/test_custom_ops.py,sha256=PenQ8zM1wj5xwiVEPVzD37pO-x90aOfFMpCRZenaKsY,5709
|
|
994
|
-
sglang/test/test_cutlass_moe.py,sha256=
|
|
995
|
-
sglang/test/test_cutlass_w4a8_moe.py,sha256=
|
|
1048
|
+
sglang/test/test_cutlass_moe.py,sha256=0kzalShZCSSbV1JLKv77mx8bXgK2wvskTuPGqK_qNnQ,10051
|
|
1049
|
+
sglang/test/test_cutlass_w4a8_moe.py,sha256=iQIZ1K43emzqI9WVKlb2fplLPcvlpm3D7qCNK-wJfa4,8924
|
|
996
1050
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
|
997
|
-
sglang/test/test_deterministic.py,sha256=
|
|
998
|
-
sglang/test/
|
|
1051
|
+
sglang/test/test_deterministic.py,sha256=ISh_2dnEgRI1Ku7lxmDKs7mwNgLrBEhKnLnvW9Uei98,15689
|
|
1052
|
+
sglang/test/test_deterministic_utils.py,sha256=vVtwq_NjH9GzSkRUn4mep-IIvgAXtw-5l6iKjYDP8SA,2133
|
|
1053
|
+
sglang/test/test_disaggregation_utils.py,sha256=k_V_vw6qCEw3iZyUeujozMBkUgGRfCWxkLyCb9ktIbk,5588
|
|
999
1054
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
|
1000
1055
|
sglang/test/test_fp4_moe.py,sha256=wvHbGMH1UBr_XVWYgX57Y2bLy9h2DPQH10_Hmf2q6iw,22436
|
|
1001
1056
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
|
1002
|
-
sglang/test/test_marlin_moe.py,sha256=
|
|
1057
|
+
sglang/test/test_marlin_moe.py,sha256=d3LsMn9qT-r-DzHKhHikRTzSPSDWDtBNuIpz35AeM20,7958
|
|
1003
1058
|
sglang/test/test_marlin_utils.py,sha256=kC7IzN364mJT9xw0nKUP1V1OK1hkw6fQTBvD4nRaOz4,5151
|
|
1004
1059
|
sglang/test/test_programs.py,sha256=R-pzgNB-h_jjdJiW50hn83-nY7z5q5XcqPwugPnVF5Y,18916
|
|
1005
|
-
sglang/test/test_utils.py,sha256
|
|
1060
|
+
sglang/test/test_utils.py,sha256=-i5Jh91gO7fDkr6PM1Lb7s7tyUqcI5v_qdhCKyDbgNg,56381
|
|
1006
1061
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1007
|
-
sglang/test/attention/test_flashattn_backend.py,sha256=
|
|
1008
|
-
sglang/test/attention/test_flashattn_mla_backend.py,sha256=
|
|
1009
|
-
sglang/test/attention/test_prefix_chunk_info.py,sha256=
|
|
1010
|
-
sglang/test/attention/test_trtllm_mla_backend.py,sha256=
|
|
1011
|
-
sglang
|
|
1012
|
-
sglang
|
|
1013
|
-
sglang
|
|
1014
|
-
sglang
|
|
1015
|
-
sglang-0.5.
|
|
1062
|
+
sglang/test/attention/test_flashattn_backend.py,sha256=Uh895KymXiRFH1pJ1NR9eSfoi6UI41YdPc4viLdUTBA,13904
|
|
1063
|
+
sglang/test/attention/test_flashattn_mla_backend.py,sha256=XW12ALYv2Ncs4t-Bz6omhYzNUQGe_P10K0gyqp9Y37U,10690
|
|
1064
|
+
sglang/test/attention/test_prefix_chunk_info.py,sha256=er0i3KGHMkw-4UZB1GCFd4oYwRcXfU5wpO1ORqpNGGA,7626
|
|
1065
|
+
sglang/test/attention/test_trtllm_mla_backend.py,sha256=UbtvkzTAqP-kHHEhhtPxVpuzG9QmyWBrFuJa0S7Z52g,54951
|
|
1066
|
+
sglang/test/longbench_v2/__init__.py,sha256=ZcOIPSyqbDI_tzB-qltXF67-4uMMPwCkkiWDVcDBDvQ,63
|
|
1067
|
+
sglang/test/longbench_v2/test_longbench_v2_eval.py,sha256=NI_Om4ODw5utUNsYjrj6nueebI4U5u4N2PKBtT5O27k,7352
|
|
1068
|
+
sglang/test/longbench_v2/validate_longbench_v2.py,sha256=mJa5Lh8XiSTXKrf5qopKuAfspSVbhoacnCkz6u4lYFQ,11635
|
|
1069
|
+
sglang/test/longbench_v2/validate_longbench_v2_standalone.py,sha256=gr0zif2c680hSyIHDVJ_NHYcrMquM3fpJ26mBtbm7zs,10909
|
|
1070
|
+
sglang-0.5.4.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
|
1071
|
+
sglang-0.5.4.dist-info/METADATA,sha256=M8BtBa6y1fGn0YOx6BJttNdVgtLNOPMbLM3t58ZNCy0,25668
|
|
1072
|
+
sglang-0.5.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
|
1073
|
+
sglang-0.5.4.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
|
1074
|
+
sglang-0.5.4.dist-info/RECORD,,
|