sglang 0.5.2rc2__py3-none-any.whl → 0.5.3rc0__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_server.py +10 -1
- sglang/bench_serving.py +257 -29
- sglang/srt/configs/__init__.py +4 -0
- sglang/srt/configs/device_config.py +3 -1
- sglang/srt/configs/dots_vlm.py +139 -0
- sglang/srt/configs/load_config.py +1 -0
- sglang/srt/configs/model_config.py +50 -6
- sglang/srt/configs/qwen3_next.py +326 -0
- sglang/srt/connector/__init__.py +8 -1
- sglang/srt/connector/remote_instance.py +82 -0
- sglang/srt/constrained/base_grammar_backend.py +48 -12
- sglang/srt/constrained/llguidance_backend.py +0 -1
- sglang/srt/constrained/outlines_backend.py +0 -1
- sglang/srt/constrained/xgrammar_backend.py +28 -9
- sglang/srt/custom_op.py +11 -1
- sglang/srt/debug_utils/dump_comparator.py +81 -44
- sglang/srt/debug_utils/dump_loader.py +97 -0
- sglang/srt/debug_utils/dumper.py +11 -3
- sglang/srt/debug_utils/text_comparator.py +73 -11
- sglang/srt/disaggregation/base/conn.py +1 -1
- sglang/srt/disaggregation/common/conn.py +15 -12
- sglang/srt/disaggregation/decode.py +21 -10
- sglang/srt/disaggregation/decode_schedule_batch_mixin.py +4 -1
- sglang/srt/disaggregation/fake/conn.py +1 -1
- sglang/srt/disaggregation/mini_lb.py +6 -445
- sglang/srt/disaggregation/mooncake/conn.py +18 -10
- sglang/srt/disaggregation/nixl/conn.py +180 -16
- sglang/srt/disaggregation/prefill.py +5 -3
- sglang/srt/disaggregation/utils.py +5 -50
- sglang/srt/distributed/parallel_state.py +24 -3
- sglang/srt/entrypoints/engine.py +38 -17
- sglang/srt/entrypoints/grpc_request_manager.py +580 -0
- sglang/srt/entrypoints/grpc_server.py +680 -0
- sglang/srt/entrypoints/http_server.py +85 -54
- sglang/srt/entrypoints/openai/protocol.py +4 -1
- sglang/srt/entrypoints/openai/serving_base.py +46 -3
- sglang/srt/entrypoints/openai/serving_chat.py +36 -16
- sglang/srt/entrypoints/openai/serving_completions.py +12 -3
- sglang/srt/entrypoints/openai/serving_embedding.py +8 -3
- sglang/srt/entrypoints/openai/serving_rerank.py +3 -1
- sglang/srt/entrypoints/openai/serving_responses.py +6 -3
- sglang/srt/entrypoints/openai/serving_score.py +1 -0
- sglang/srt/eplb/eplb_manager.py +2 -2
- sglang/srt/eplb/expert_distribution.py +26 -13
- sglang/srt/eplb/expert_location.py +8 -3
- sglang/srt/eplb/expert_location_updater.py +1 -1
- sglang/srt/function_call/base_format_detector.py +3 -6
- sglang/srt/function_call/ebnf_composer.py +11 -9
- sglang/srt/function_call/function_call_parser.py +6 -0
- sglang/srt/function_call/glm4_moe_detector.py +1 -1
- sglang/srt/function_call/qwen3_coder_detector.py +1 -1
- sglang/srt/grpc/__init__.py +1 -0
- sglang/srt/grpc/sglang_scheduler_pb2.py +106 -0
- sglang/srt/grpc/sglang_scheduler_pb2.pyi +427 -0
- sglang/srt/grpc/sglang_scheduler_pb2_grpc.py +236 -0
- sglang/srt/hf_transformers_utils.py +4 -0
- sglang/srt/layers/activation.py +142 -9
- sglang/srt/layers/attention/ascend_backend.py +11 -4
- sglang/srt/layers/attention/fla/chunk.py +242 -0
- sglang/srt/layers/attention/fla/chunk_delta_h.py +314 -0
- sglang/srt/layers/attention/fla/chunk_o.py +178 -0
- sglang/srt/layers/attention/fla/chunk_scaled_dot_kkt.py +151 -0
- sglang/srt/layers/attention/fla/cumsum.py +300 -0
- sglang/srt/layers/attention/fla/fused_recurrent.py +640 -0
- sglang/srt/layers/attention/fla/fused_sigmoid_gating_recurrent.py +232 -0
- sglang/srt/layers/attention/fla/index.py +37 -0
- sglang/srt/layers/attention/fla/l2norm.py +150 -0
- sglang/srt/layers/attention/fla/layernorm_gated.py +326 -0
- sglang/srt/layers/attention/fla/op.py +66 -0
- sglang/srt/layers/attention/fla/solve_tril.py +465 -0
- sglang/srt/layers/attention/fla/utils.py +331 -0
- sglang/srt/layers/attention/fla/wy_fast.py +158 -0
- sglang/srt/layers/attention/flashinfer_backend.py +6 -4
- sglang/srt/layers/attention/flashinfer_mla_backend.py +16 -12
- sglang/srt/layers/attention/hybrid_attn_backend.py +57 -50
- sglang/srt/layers/attention/hybrid_linear_attn_backend.py +602 -0
- sglang/srt/layers/attention/intel_amx_backend.py +3 -0
- sglang/srt/layers/attention/mamba/causal_conv1d.py +128 -0
- sglang/srt/layers/attention/mamba/causal_conv1d_triton.py +1052 -0
- sglang/srt/layers/attention/mamba/mamba.py +64 -0
- sglang/srt/layers/attention/torch_native_backend.py +12 -6
- sglang/srt/layers/attention/triton_backend.py +18 -1
- sglang/srt/layers/attention/trtllm_mla_backend.py +124 -31
- sglang/srt/layers/attention/wave_ops/decode_attention.py +2 -4
- sglang/srt/layers/attention/wave_ops/extend_attention.py +1 -3
- sglang/srt/layers/dp_attention.py +30 -1
- sglang/srt/layers/layernorm.py +32 -15
- sglang/srt/layers/linear.py +34 -3
- sglang/srt/layers/logits_processor.py +29 -10
- sglang/srt/layers/moe/__init__.py +2 -1
- sglang/srt/layers/moe/cutlass_w4a8_moe.py +3 -3
- sglang/srt/layers/moe/ep_moe/kernels.py +1 -1
- sglang/srt/layers/moe/ep_moe/layer.py +182 -62
- sglang/srt/layers/moe/flashinfer_cutedsl_moe.py +156 -0
- sglang/srt/layers/moe/fused_moe_native.py +5 -3
- sglang/srt/layers/moe/fused_moe_triton/configs/{triton_3_4_0/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json → triton_3_3_1/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json } +35 -35
- 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 +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=512,device_name=NVIDIA_H20.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H20-3e.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H200.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=256,device_name=NVIDIA_H20-3e.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=256,device_name=NVIDIA_H200.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=64,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=64,device_name=NVIDIA_H200.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +5 -2
- sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py +1 -1
- sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py +23 -20
- sglang/srt/layers/moe/fused_moe_triton/layer.py +61 -59
- sglang/srt/layers/moe/moe_runner/__init__.py +2 -1
- sglang/srt/layers/moe/moe_runner/base.py +274 -1
- sglang/srt/layers/moe/moe_runner/runner.py +80 -0
- sglang/srt/layers/moe/moe_runner/triton.py +448 -0
- sglang/srt/layers/moe/token_dispatcher/__init__.py +16 -4
- sglang/srt/layers/moe/token_dispatcher/{base_dispatcher.py → base.py} +67 -17
- sglang/srt/layers/moe/token_dispatcher/deepep.py +43 -39
- sglang/srt/layers/moe/token_dispatcher/standard.py +44 -2
- sglang/srt/layers/moe/topk.py +30 -9
- sglang/srt/layers/moe/utils.py +12 -6
- sglang/srt/layers/quantization/awq.py +19 -7
- sglang/srt/layers/quantization/base_config.py +11 -6
- sglang/srt/layers/quantization/blockwise_int8.py +38 -27
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +50 -30
- sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +13 -1
- sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py +27 -0
- sglang/srt/layers/quantization/fp8.py +76 -47
- sglang/srt/layers/quantization/fp8_utils.py +50 -31
- sglang/srt/layers/quantization/gptq.py +25 -17
- sglang/srt/layers/quantization/modelopt_quant.py +147 -47
- sglang/srt/layers/quantization/moe_wna16.py +21 -18
- sglang/srt/layers/quantization/mxfp4.py +64 -40
- sglang/srt/layers/quantization/quark/quark_moe.py +32 -27
- sglang/srt/layers/quantization/unquant.py +135 -47
- sglang/srt/layers/quantization/w4afp8.py +30 -17
- sglang/srt/layers/quantization/w8a8_fp8.py +35 -20
- sglang/srt/layers/quantization/w8a8_int8.py +76 -38
- sglang/srt/layers/sampler.py +162 -18
- sglang/srt/lora/backend/base_backend.py +50 -8
- sglang/srt/lora/backend/triton_backend.py +90 -2
- sglang/srt/lora/layers.py +32 -0
- sglang/srt/lora/lora.py +4 -1
- sglang/srt/lora/lora_manager.py +35 -112
- sglang/srt/lora/mem_pool.py +24 -10
- sglang/srt/lora/utils.py +18 -9
- sglang/srt/managers/async_dynamic_batch_tokenizer.py +170 -0
- sglang/srt/managers/cache_controller.py +158 -160
- sglang/srt/managers/data_parallel_controller.py +105 -35
- sglang/srt/managers/detokenizer_manager.py +8 -4
- sglang/srt/managers/disagg_service.py +46 -0
- sglang/srt/managers/io_struct.py +199 -12
- sglang/srt/managers/mm_utils.py +1 -0
- sglang/srt/managers/multi_tokenizer_mixin.py +350 -400
- sglang/srt/managers/schedule_batch.py +77 -56
- sglang/srt/managers/schedule_policy.py +1 -1
- sglang/srt/managers/scheduler.py +187 -39
- sglang/srt/managers/scheduler_metrics_mixin.py +4 -3
- sglang/srt/managers/scheduler_output_processor_mixin.py +55 -11
- sglang/srt/managers/scheduler_profiler_mixin.py +1 -1
- sglang/srt/managers/tokenizer_communicator_mixin.py +569 -0
- sglang/srt/managers/tokenizer_manager.py +259 -519
- sglang/srt/managers/tp_worker.py +53 -4
- sglang/srt/managers/tp_worker_overlap_thread.py +42 -19
- sglang/srt/mem_cache/hicache_storage.py +3 -23
- sglang/srt/mem_cache/hiradix_cache.py +103 -43
- sglang/srt/mem_cache/memory_pool.py +347 -48
- sglang/srt/mem_cache/memory_pool_host.py +105 -46
- sglang/srt/mem_cache/radix_cache.py +0 -2
- sglang/srt/mem_cache/storage/hf3fs/hf3fs_client.py +164 -0
- sglang/srt/mem_cache/storage/hf3fs/{client_hf3fs.py → hf3fs_usrbio_client.py} +5 -1
- sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py +86 -4
- sglang/srt/mem_cache/storage/lmcache/lmc_radix_cache.py +280 -0
- sglang/srt/mem_cache/storage/lmcache/unit_test.py +121 -0
- sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py +49 -7
- sglang/srt/mem_cache/swa_radix_cache.py +0 -2
- sglang/srt/metrics/collector.py +493 -76
- sglang/srt/metrics/startup_func_log_and_timer.py +150 -0
- sglang/srt/model_executor/cpu_graph_runner.py +640 -0
- sglang/srt/model_executor/cuda_graph_runner.py +13 -5
- sglang/srt/model_executor/forward_batch_info.py +59 -2
- sglang/srt/model_executor/model_runner.py +356 -29
- sglang/srt/model_loader/__init__.py +9 -3
- sglang/srt/model_loader/loader.py +128 -4
- sglang/srt/model_loader/weight_utils.py +2 -1
- sglang/srt/models/apertus.py +686 -0
- sglang/srt/models/bailing_moe.py +798 -218
- sglang/srt/models/bailing_moe_nextn.py +168 -0
- sglang/srt/models/deepseek_v2.py +109 -15
- sglang/srt/models/dots_vlm.py +174 -0
- sglang/srt/models/dots_vlm_vit.py +337 -0
- sglang/srt/models/ernie4.py +1 -1
- sglang/srt/models/gemma3n_mm.py +1 -1
- sglang/srt/models/glm4_moe.py +1 -1
- sglang/srt/models/glm4v.py +4 -2
- sglang/srt/models/glm4v_moe.py +3 -0
- sglang/srt/models/gpt_oss.py +1 -1
- sglang/srt/models/llama4.py +9 -0
- sglang/srt/models/llama_eagle3.py +13 -0
- sglang/srt/models/longcat_flash.py +2 -2
- sglang/srt/models/mllama4.py +25 -0
- sglang/srt/models/opt.py +637 -0
- sglang/srt/models/qwen2.py +7 -0
- sglang/srt/models/qwen2_5_vl.py +27 -3
- sglang/srt/models/qwen2_moe.py +56 -12
- sglang/srt/models/qwen3_moe.py +1 -1
- sglang/srt/models/qwen3_next.py +1042 -0
- sglang/srt/models/qwen3_next_mtp.py +112 -0
- sglang/srt/models/step3_vl.py +1 -1
- sglang/srt/multimodal/processors/dots_vlm.py +99 -0
- sglang/srt/multimodal/processors/glm4v.py +9 -9
- sglang/srt/multimodal/processors/internvl.py +141 -129
- sglang/srt/multimodal/processors/qwen_vl.py +15 -5
- sglang/srt/offloader.py +27 -3
- sglang/srt/remote_instance_weight_loader_utils.py +69 -0
- sglang/srt/sampling/sampling_batch_info.py +18 -15
- sglang/srt/server_args.py +276 -35
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +5 -0
- sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py +10 -1
- sglang/srt/speculative/eagle_utils.py +0 -2
- sglang/srt/speculative/eagle_worker.py +43 -4
- sglang/srt/speculative/spec_info.py +5 -0
- sglang/srt/speculative/standalone_worker.py +109 -0
- sglang/srt/tracing/trace.py +552 -0
- sglang/srt/utils.py +34 -3
- sglang/srt/weight_sync/utils.py +1 -1
- sglang/test/attention/test_trtllm_mla_backend.py +169 -5
- sglang/test/runners.py +4 -0
- sglang/test/test_cutlass_moe.py +24 -6
- sglang/test/test_disaggregation_utils.py +66 -0
- sglang/test/test_fp4_moe.py +370 -1
- sglang/test/test_utils.py +28 -1
- sglang/utils.py +11 -0
- sglang/version.py +1 -1
- {sglang-0.5.2rc2.dist-info → sglang-0.5.3rc0.dist-info}/METADATA +59 -123
- {sglang-0.5.2rc2.dist-info → sglang-0.5.3rc0.dist-info}/RECORD +237 -178
- sglang/srt/disaggregation/launch_lb.py +0 -118
- {sglang-0.5.2rc2.dist-info → sglang-0.5.3rc0.dist-info}/WHEEL +0 -0
- {sglang-0.5.2rc2.dist-info → sglang-0.5.3rc0.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.5.2rc2.dist-info → sglang-0.5.3rc0.dist-info}/top_level.txt +0 -0
@@ -1,15 +1,15 @@
|
|
1
1
|
sglang/__init__.py,sha256=CK60u1J439CJZaPihWqlDjFZ8doIC-5YgIYz-E1PIh4,1823
|
2
2
|
sglang/bench_offline_throughput.py,sha256=Bge0KG4Uiv9CHsxDnqKdXJmG_TcxM4blz3CmvLmDRvM,14815
|
3
3
|
sglang/bench_one_batch.py,sha256=ITGCBFPksSyoXPEgAqZruGY2ZUPyOoc111jf1nil0go,23137
|
4
|
-
sglang/bench_one_batch_server.py,sha256=
|
5
|
-
sglang/bench_serving.py,sha256=
|
4
|
+
sglang/bench_one_batch_server.py,sha256=WQeZCpqdJIUIel950_uzgH2d2LYUXXnIkwcspGI37xs,14967
|
5
|
+
sglang/bench_serving.py,sha256=DiiubFyUVMMaOZ1kfMna3WS73AT4JKy4A4Tlt_bns-w,87627
|
6
6
|
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
7
7
|
sglang/compile_deep_gemm.py,sha256=EsgboGA-MK3Rvx9TlUJPLxJ5LBira4bTcHJLKEp1H6k,6488
|
8
8
|
sglang/global_config.py,sha256=ZMTux_PsGnvkyJ0kTFwhTdbnFwIjjpGDogut_9Lu4Vo,1732
|
9
9
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
10
10
|
sglang/profiler.py,sha256=JCpZzlDhahoiPlPi5IG3n7GFrQHxfHEB6ELie3Ck55w,4397
|
11
|
-
sglang/utils.py,sha256=
|
12
|
-
sglang/version.py,sha256=
|
11
|
+
sglang/utils.py,sha256=q2MyArgYal5PeX1cai5Xp7DLAndUVGqp1JgmYY69_c4,16838
|
12
|
+
sglang/version.py,sha256=IaibyW4nPGE2sYdcYwKxJFflblb1AMxl7TBJUVG67Gk,25
|
13
13
|
sglang/eval/llama3_eval.py,sha256=mLNRZJIqV4CfqrY8UGnJEcHw2Xsyr1eyYZgFSUFYr1g,9997
|
14
14
|
sglang/eval/loogle_eval.py,sha256=-CC2s2kh5qUoDrHRkQVkC_jNvBgNojXbf456ny5s78s,4557
|
15
15
|
sglang/lang/api.py,sha256=rcp3GeoyZhmJ0GDLPRkuZNcxd0TBJy_wfUDpcmQoqW8,7210
|
@@ -29,80 +29,84 @@ sglang/srt/_custom_ops.py,sha256=9GPNUyqnybgvUnzdQ8n5_NgluHmQNw0Gptos0iLPfrY,534
|
|
29
29
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
30
30
|
sglang/srt/bench_utils.py,sha256=zNTsTBUta27XxojgvR5p5X9M0v1MFzZ7dcX9TMq4NvQ,4348
|
31
31
|
sglang/srt/constants.py,sha256=0i-tEwG2BSYNDy96MxnGHV5HnBELkYcnsVGsE-R18o0,93
|
32
|
-
sglang/srt/custom_op.py,sha256=
|
33
|
-
sglang/srt/hf_transformers_utils.py,sha256=
|
32
|
+
sglang/srt/custom_op.py,sha256=m5F7x3LHlnOuesmcNmJtIWsfHGFLBJ807vKc05Gu1D0,3312
|
33
|
+
sglang/srt/hf_transformers_utils.py,sha256=UuKeXYCjRBMA9ppPk27rGHE4JAMXb9fmYqEu1KGFo58,15808
|
34
34
|
sglang/srt/host_shared_memory.py,sha256=00TgVm3PNCl4rTPJZChG5uu4I5hd_Xf587r39tibmIg,2274
|
35
|
-
sglang/srt/offloader.py,sha256=
|
35
|
+
sglang/srt/offloader.py,sha256=cYON5jZErAp88Sh5JseaRw0B2Ho2MQz9smgvrTc-2KA,18765
|
36
36
|
sglang/srt/operations.py,sha256=za_h1_kcR1Te6-i_r0i_zAeumbmIRhLK2pS31sukkrw,6089
|
37
37
|
sglang/srt/operations_strategy.py,sha256=-w6GI2VgSGvORy3pUWRAJo6244ykSW1ZBV1Dx0fZlHA,7138
|
38
38
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
39
39
|
sglang/srt/poll_based_barrier.py,sha256=9vjn32ROlSueEk7EuZjWKUrrL7XVR9KJsSVliGTYB_4,937
|
40
|
-
sglang/srt/
|
40
|
+
sglang/srt/remote_instance_weight_loader_utils.py,sha256=_HnQD1Ab-Wv9oATOmwJe6aQaQD_Gs_yG9EsDCGJQWfs,2881
|
41
|
+
sglang/srt/server_args.py,sha256=3bWmsVF296HQWC7CVfRSa0EU5DFo2hrRfAEUJ3tfBk8,118613
|
41
42
|
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
42
43
|
sglang/srt/two_batch_overlap.py,sha256=UykF5nC2rja3Hvmu0D9glqKdVRIEhQGPV84Jm7veopQ,34150
|
43
|
-
sglang/srt/utils.py,sha256=
|
44
|
+
sglang/srt/utils.py,sha256=VmMJ9Ear1SZapYepidP5jGmTGCfefa3EajeNHPhMGcc,96460
|
44
45
|
sglang/srt/warmup.py,sha256=zldxhMlXpclRAJXmfBjJNUJd1eDizVdysibBvQyTVuA,1782
|
45
|
-
sglang/srt/configs/__init__.py,sha256=
|
46
|
+
sglang/srt/configs/__init__.py,sha256=albyONB4cZYRjfLBr2kMReUHApKS-GqVHtiq9SeyUYk,989
|
46
47
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
47
48
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
48
49
|
sglang/srt/configs/deepseekvl2.py,sha256=sYMmoy5_LlDXht7MTi4QGYOaiE8iMGUO44bnuOu4i8I,23683
|
49
|
-
sglang/srt/configs/device_config.py,sha256=
|
50
|
+
sglang/srt/configs/device_config.py,sha256=1Iaxrk65bJsCWV3E2cDfiap_T_xJIIj9oFVn9y6v0EI,515
|
51
|
+
sglang/srt/configs/dots_vlm.py,sha256=PYoSrT-sRoykfNhdXFauqv21Sb54iavjYD3F09xww3U,5176
|
50
52
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
51
53
|
sglang/srt/configs/internvl.py,sha256=rIC-CBWJHy-Mjmk0_H3YcvVmZzeCRbXGo3dQMex-yeg,28141
|
52
54
|
sglang/srt/configs/janus_pro.py,sha256=yI2c_aWBIKiTcK6RZxK6hq8CIxyYRH_NN8uaSNKsrKI,19156
|
53
55
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
54
56
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
55
|
-
sglang/srt/configs/load_config.py,sha256=
|
57
|
+
sglang/srt/configs/load_config.py,sha256=WnkzQqHlBWFZWsCNY1k6ohpJ-YFsEAJJDjGGkkTkWG0,3349
|
56
58
|
sglang/srt/configs/longcat_flash.py,sha256=Qp25xJVLq2K72Z80cXhcJxtqhagAdiPySDoevuT0Sno,3589
|
57
|
-
sglang/srt/configs/model_config.py,sha256=
|
59
|
+
sglang/srt/configs/model_config.py,sha256=qX2w_Ty3ibOLsisLJERGQbwYRAVV3p6KVGZtODxtrWo,33832
|
60
|
+
sglang/srt/configs/qwen3_next.py,sha256=MVMDzdwlxrdar_6p6n9HjaXAei_giFfXlQNJAWpSLQ4,15794
|
58
61
|
sglang/srt/configs/step3_vl.py,sha256=_Otgnym57DVgB_kZ__8c1_Ys5gSalA_K0ZuVjcG51T0,4845
|
59
62
|
sglang/srt/configs/update_config.py,sha256=GEf-XhL8JPrbX9-Hz8V7S3M6YTg76DVdIhc_4YdMDtc,6291
|
60
63
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
61
|
-
sglang/srt/connector/__init__.py,sha256=
|
64
|
+
sglang/srt/connector/__init__.py,sha256=zPuaRKulJsrDyT3OtN9wUT-4fqQBX-cJr2fZUB0_KPM,1562
|
62
65
|
sglang/srt/connector/base_connector.py,sha256=LCKsTX_yWHclPrzNNB1fLwVCN8rIDKZaZhqHQ54B9MU,2774
|
63
66
|
sglang/srt/connector/redis.py,sha256=K3fJSm2rZsd0R_KkICV3jIWKtrwxXE1tYktWnovLbz4,2514
|
67
|
+
sglang/srt/connector/remote_instance.py,sha256=X_PIZFvZPsnUZ_54AgnzR0NdUfi6ClwQVlNexZatkXU,2710
|
64
68
|
sglang/srt/connector/s3.py,sha256=hn5Ow9Y6ItS8RMJDwnTQe5QaiQ7HKMgiwggE9QnUewM,3743
|
65
69
|
sglang/srt/connector/utils.py,sha256=isTvxauz1_8no5MW6p8Bwj2H9mQkweaRO_RSwAPA7R8,983
|
66
70
|
sglang/srt/connector/serde/__init__.py,sha256=zuleyYN-jrDyiPiXjTbQKA27llb4H7HuDTZcBwrLk1U,707
|
67
71
|
sglang/srt/connector/serde/safe_serde.py,sha256=XSjb9mRv1HqeG6Jiw633EOQYlrcI23Q21UluYqPZaWA,760
|
68
72
|
sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOUIhF0ZA,1004
|
69
|
-
sglang/srt/constrained/base_grammar_backend.py,sha256=
|
70
|
-
sglang/srt/constrained/llguidance_backend.py,sha256=
|
71
|
-
sglang/srt/constrained/outlines_backend.py,sha256=
|
73
|
+
sglang/srt/constrained/base_grammar_backend.py,sha256=k0gr9BUrnYjggRlxVCOjFtXFgbGRCAI6NWjqwuPp9PU,8074
|
74
|
+
sglang/srt/constrained/llguidance_backend.py,sha256=JkA_59nZ4zd8ciGvXsZ-OEsGCyQMoIxBO8QXIUqAUn4,6161
|
75
|
+
sglang/srt/constrained/outlines_backend.py,sha256=t4gkO9AX8xfYulvhNx0n-p1kUavJnCjE9XjwN1Z4BV4,6883
|
72
76
|
sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
|
73
77
|
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
74
|
-
sglang/srt/constrained/xgrammar_backend.py,sha256=
|
78
|
+
sglang/srt/constrained/xgrammar_backend.py,sha256=SNeF_bq5VodQUkMHSwAxPbxDatdsqnTqe3N3Qi-jchM,9225
|
75
79
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
76
80
|
sglang/srt/debug_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
77
|
-
sglang/srt/debug_utils/dump_comparator.py,sha256=
|
78
|
-
sglang/srt/debug_utils/
|
79
|
-
sglang/srt/debug_utils/
|
80
|
-
sglang/srt/
|
81
|
-
sglang/srt/disaggregation/
|
81
|
+
sglang/srt/debug_utils/dump_comparator.py,sha256=3rWdv4BQXTDtB3z5ao9VPN5lK31ImKf2zMWX7f0Xe6s,5394
|
82
|
+
sglang/srt/debug_utils/dump_loader.py,sha256=RzWpl7RsDRw98DJMEvf6U9c9fPiobyeWI8opmRaRGGA,2632
|
83
|
+
sglang/srt/debug_utils/dumper.py,sha256=yqxsa_I_DoCeHkDoXDgFXO0AcBzXSkPMFJ2JG73PSRA,3291
|
84
|
+
sglang/srt/debug_utils/text_comparator.py,sha256=NLJdjUikW--bWnGQWIeFJesyuvZ2Vni2S53fIED-m8s,7370
|
85
|
+
sglang/srt/disaggregation/decode.py,sha256=ahZOvQUdJmJztnUkAh9Ub_egP-YMPaLle8R_4NGoSBE,35029
|
86
|
+
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=yWrPKAQ4x00K9ZP2tLJYcdgCT4EsMzOnMsaLbBGNUT8,6829
|
82
87
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
83
|
-
sglang/srt/disaggregation/
|
84
|
-
sglang/srt/disaggregation/
|
85
|
-
sglang/srt/disaggregation/
|
86
|
-
sglang/srt/disaggregation/utils.py,sha256=evdv4AkQxJzTqdO0jrdAr7vHUbBSCEXMzNREh0FoRLc,12294
|
88
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=JY2uCeUM3Zk3FdGWmCQBY3LeiJ5FM1PlrqAW8wJTTHI,395
|
89
|
+
sglang/srt/disaggregation/prefill.py,sha256=jgZN8YmgL4wGSN2GDV88sUHfSyG3bpLg3Cb3kbEGzgo,36350
|
90
|
+
sglang/srt/disaggregation/utils.py,sha256=DvE3nj8GdoD4N_1rSpP1R2gSV4wEMWRACqfmxR27qhg,10898
|
87
91
|
sglang/srt/disaggregation/ascend/__init__.py,sha256=-lxnica6fZYmYNpKwmE8yESUpQ5Sxf2DiZoBHzboKc8,146
|
88
92
|
sglang/srt/disaggregation/ascend/conn.py,sha256=EuCsFMxwxDp7jt8K2uyTtRlIk0Vi5A_VBz6hKYwybhU,4119
|
89
93
|
sglang/srt/disaggregation/ascend/transfer_engine.py,sha256=_4PszsQL6wICdg5cqpR2N9TbZpUY6bBX8tgE3xeaYfc,2137
|
90
94
|
sglang/srt/disaggregation/base/__init__.py,sha256=4VwUv0aWxwmVL1049XK82aLTNxmt0WY5RPy9li-wyVk,160
|
91
|
-
sglang/srt/disaggregation/base/conn.py,sha256=
|
95
|
+
sglang/srt/disaggregation/base/conn.py,sha256=0CGEv-B24woyDBdEgQwT8Gqz10Uox3gCgWiCxznXkwQ,2912
|
92
96
|
sglang/srt/disaggregation/common/__init__.py,sha256=7yl-EGLMVKRpBUaGF_7lwAsw2J_mqpRZV0238VGxD9o,126
|
93
|
-
sglang/srt/disaggregation/common/conn.py,sha256=
|
97
|
+
sglang/srt/disaggregation/common/conn.py,sha256=_f4JfgffnV0wThhKVhBUGhRt-_smQBE6WwyPAo0C84s,17190
|
94
98
|
sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeKVPMWPcB5ywbE,1194
|
95
99
|
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
96
|
-
sglang/srt/disaggregation/fake/conn.py,sha256=
|
100
|
+
sglang/srt/disaggregation/fake/conn.py,sha256=qsN5SEQLMenALxYC3x7GYZprhUQyRje5ldNwjkT6OPw,2283
|
97
101
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
98
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
102
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=27UIE4ha8ELORhkPZec26LLGN_gEhlazyu1EeWDxwwc,71702
|
99
103
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=O-XRmQ3QwD6RuiyRgw4ZohSrFkuPdppV_eDBMUXn0jk,5884
|
100
104
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
101
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
105
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=AEyQ_k-LQ3rBVubdbqZ_9XCZ8xoX9ORpOdQVwY3istU,27010
|
102
106
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
103
107
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
104
108
|
sglang/srt/distributed/naive_distributed.py,sha256=5Kcfapzz61G3TtScTZrHoWa4bf6Vr27GlMcBAGMz7tQ,3260
|
105
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
109
|
+
sglang/srt/distributed/parallel_state.py,sha256=goztGivgPYGRG6uOIMnPMYKx_CdQquKLQO2m8gcpS-0,66530
|
106
110
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
107
111
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
108
112
|
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=Q1kkKPKFPV0QMmKLyjOBlOnX8-Pr4UeGBZYkG6j0gc0,16570
|
@@ -118,59 +122,65 @@ sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=IrSrnpZnii0E
|
|
118
122
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
119
123
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
120
124
|
sglang/srt/entrypoints/context.py,sha256=aD-94xkD0komuGO5gtYUoJKCHdc4hAipMxQt04yVRGA,8030
|
121
|
-
sglang/srt/entrypoints/engine.py,sha256
|
125
|
+
sglang/srt/entrypoints/engine.py,sha256=-aHzWPqLbRZhPwypTdrDyq9SupK3tWc1WOKq8OhccyA,34202
|
126
|
+
sglang/srt/entrypoints/grpc_request_manager.py,sha256=kUXR8svKfCojEjdmayzKup3I9rWRsVWHgau6KrvZVtk,20096
|
127
|
+
sglang/srt/entrypoints/grpc_server.py,sha256=AvyPTTF9qKY9bvRcZg_eIAK8Ij9uJReg-9vcWicSuEM,25407
|
122
128
|
sglang/srt/entrypoints/harmony_utils.py,sha256=01T-A5GBUm2b306PcxNEg2rfx4cykBcqNYrzcXTWBlc,13590
|
123
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
129
|
+
sglang/srt/entrypoints/http_server.py,sha256=xqO_GidmTgPjfwpWfDkqVu-zgefI9_gS_pfWpqqoLyM,50887
|
124
130
|
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
125
131
|
sglang/srt/entrypoints/tool.py,sha256=aAXEjBqkr5j6_IgRL8fZCKgoDPY2TikM20-LQXU9TaI,2709
|
126
132
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
127
|
-
sglang/srt/entrypoints/openai/protocol.py,sha256=
|
128
|
-
sglang/srt/entrypoints/openai/serving_base.py,sha256=
|
129
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
130
|
-
sglang/srt/entrypoints/openai/serving_completions.py,sha256=
|
131
|
-
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=
|
132
|
-
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=
|
133
|
-
sglang/srt/entrypoints/openai/serving_responses.py,sha256=
|
134
|
-
sglang/srt/entrypoints/openai/serving_score.py,sha256=
|
133
|
+
sglang/srt/entrypoints/openai/protocol.py,sha256=WAmFQv-dw48d1lIIFMYDFZ3YkAhDKa5y0YDL_d9NP-k,28864
|
134
|
+
sglang/srt/entrypoints/openai/serving_base.py,sha256=f6yz54jvEEuntufhnTnKPFl444ZIlVw1zVUVb3g4gcQ,6953
|
135
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=IrDswjZSLuC3atqB-aKK2-_D5Ld1UVABOjFlyDdF0LI,43590
|
136
|
+
sglang/srt/entrypoints/openai/serving_completions.py,sha256=7i5XyOLJLdw-LWuQm5I0WEBsFLZWiw9j2YuhfyZA9r0,18148
|
137
|
+
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=SomzA0ocIuOXnJE3wlKnDjC6Ou3zWO-ISfuMtEwljRs,6396
|
138
|
+
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=G79XdomjzLhH1YCbGR4alSxWO9NNmi7U-YSPsH61cjk,3379
|
139
|
+
sglang/srt/entrypoints/openai/serving_responses.py,sha256=DnNGNJqmHu4ZB52p9jTxneASgTSEl14fCUGUBWx46B0,53482
|
140
|
+
sglang/srt/entrypoints/openai/serving_score.py,sha256=LuwXzWRAMm-xMK8ZjP3JaJ84Gxjr0Oi-e3keCsIgK38,1992
|
135
141
|
sglang/srt/entrypoints/openai/tool_server.py,sha256=rRNGELPV5RHONp55MYkO4_b0NPsPffJnWg-gMYwDSTc,5659
|
136
142
|
sglang/srt/entrypoints/openai/usage_processor.py,sha256=9LTB5rqdRuMKyZrIXiUBuF_WKaSg9X45YdzERDxbtCY,2746
|
137
143
|
sglang/srt/entrypoints/openai/utils.py,sha256=DT9quW0F1DX1P9NAuMxpERgXcNYKKtm7rd7J1m7EaDQ,2112
|
138
144
|
sglang/srt/eplb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
139
|
-
sglang/srt/eplb/eplb_manager.py,sha256=
|
140
|
-
sglang/srt/eplb/expert_distribution.py,sha256=
|
141
|
-
sglang/srt/eplb/expert_location.py,sha256=
|
145
|
+
sglang/srt/eplb/eplb_manager.py,sha256=e8HMGzZb2QFRGdS7JZIFSy8cOIlxOlGRY-ef7Wei0Sw,4364
|
146
|
+
sglang/srt/eplb/expert_distribution.py,sha256=gd3PktGCSqHLjB5XHhTSA-OtaDVYw-taExCe7NOHM9E,32939
|
147
|
+
sglang/srt/eplb/expert_location.py,sha256=UX87bd00DXOs53ugCiZzqias1ir51dn1KevWpIDAiRc,17155
|
142
148
|
sglang/srt/eplb/expert_location_dispatch.py,sha256=vA0o-7bXf847BQAVCqElWKEpofZLAIsir_d0pew2KNQ,4178
|
143
|
-
sglang/srt/eplb/expert_location_updater.py,sha256=
|
149
|
+
sglang/srt/eplb/expert_location_updater.py,sha256=ScoyCJbtJNQLriQXJNZTV2-5G8-tR3AocZDK3ujMaJk,21172
|
144
150
|
sglang/srt/eplb/eplb_algorithms/__init__.py,sha256=c6fo4qM8N0p5DyyfGp9fxqc2wkxvzSJBzJFRG1I1leg,1959
|
145
151
|
sglang/srt/eplb/eplb_algorithms/deepseek.py,sha256=mMZT7zAAArccdRS0xXxifvMb3qn9enSt426uUTKeiq4,8340
|
146
152
|
sglang/srt/eplb/eplb_algorithms/deepseek_vec.py,sha256=Vzy5Iarua1VgVHzjBNZaVV_vt1LY1BLtJz7PmzB701k,10654
|
147
153
|
sglang/srt/eplb/eplb_simulator/__init__.py,sha256=HIZaXqsvsOCMMJ81dSs1afSGZ5G6OiOZEtHpltyzzjY,21
|
148
154
|
sglang/srt/eplb/eplb_simulator/reader.py,sha256=OlsWqsuXqVQY7PfvvrP-vsl2Ww2Kg4vD_K9BltM_QHo,1828
|
149
|
-
sglang/srt/function_call/base_format_detector.py,sha256=
|
155
|
+
sglang/srt/function_call/base_format_detector.py,sha256=DunwyYJxLcwrD-iHDXX9uqJ5S8zMJhUXfzHiBgbXaZ0,15728
|
150
156
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
151
157
|
sglang/srt/function_call/deepseekv31_detector.py,sha256=hpRjjv219mH0v1PQpMvj_gezrP7PwvLiNbBKOTCSC3U,9731
|
152
158
|
sglang/srt/function_call/deepseekv3_detector.py,sha256=DhO3tUX1nvFlfRkHJ1Vm_7OMXFFTvWBA9u9SZKFAwuQ,9710
|
153
|
-
sglang/srt/function_call/ebnf_composer.py,sha256=
|
154
|
-
sglang/srt/function_call/function_call_parser.py,sha256=
|
155
|
-
sglang/srt/function_call/glm4_moe_detector.py,sha256=
|
159
|
+
sglang/srt/function_call/ebnf_composer.py,sha256=OpjfvYowLlMLnxz5fwS7zv5-d43_ZwO9ucGAMsILvm4,15321
|
160
|
+
sglang/srt/function_call/function_call_parser.py,sha256=sMZVcdzBuBbiqHW2q8iLDdAMtScHHiSMYOsq2i9M-MY,8506
|
161
|
+
sglang/srt/function_call/glm4_moe_detector.py,sha256=2mxC4c93lUimNFcho3lAfj54Qm-evRph_NMCpH3H5B4,6941
|
156
162
|
sglang/srt/function_call/gpt_oss_detector.py,sha256=HLthoD4NHl3EKM04R5UL0CvQEYuwFtwtGH8DwHRTCoY,8306
|
157
163
|
sglang/srt/function_call/kimik2_detector.py,sha256=u6GXTAcvqWstkuDgxZMeKlpp9zu3V4OTZ8yaplLxEGM,10109
|
158
164
|
sglang/srt/function_call/llama32_detector.py,sha256=trZja7IXc2IWUko5PRj7p4pRU6XCVjtxr-7qJNr0EWo,3647
|
159
165
|
sglang/srt/function_call/mistral_detector.py,sha256=Ts2HrJdu5r2lCCMVKPZfnCds9pt1K5H1EaOQrF_HD60,4686
|
160
166
|
sglang/srt/function_call/pythonic_detector.py,sha256=yAatItKtVDf9uhlB78wPWKP3fbefLJDNGGzFV5ey-YA,8756
|
161
167
|
sglang/srt/function_call/qwen25_detector.py,sha256=nv83_sipZMU6Vie3J4HeNiZVCSRU5ei7601j50779HA,5181
|
162
|
-
sglang/srt/function_call/qwen3_coder_detector.py,sha256=
|
168
|
+
sglang/srt/function_call/qwen3_coder_detector.py,sha256=fyiF0WkNwozlKZQy0G903hj-ZAyvEgkFC8l20FVOVX8,14299
|
163
169
|
sglang/srt/function_call/step3_detector.py,sha256=SAibrispu0peDQzqOG2-V93KGHtV6Ud7a38vlnhTunA,17442
|
164
170
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
165
|
-
sglang/srt/
|
171
|
+
sglang/srt/grpc/__init__.py,sha256=dPeDsMRMW8WyHD6jolIpIlvlJsYLAhwewHhCTdu1MAE,21
|
172
|
+
sglang/srt/grpc/sglang_scheduler_pb2.py,sha256=UlEEQlqRPn9bpzU3yuKk5jnZ2oTY5vkHCjk6whpJkxw,13638
|
173
|
+
sglang/srt/grpc/sglang_scheduler_pb2.pyi,sha256=Ern-QjPT0YJuSq_7VLQI7uq6pbE7QjIXC0gTOgm1BQA,22662
|
174
|
+
sglang/srt/grpc/sglang_scheduler_pb2_grpc.py,sha256=SIk7q03hSa_WjkHdSCmp7a0-e4wP27B9ykJZbOlu9-g,8954
|
175
|
+
sglang/srt/layers/activation.py,sha256=c02kRmXRmUKs3aNZCWcxcvoYyuttx0E88MiNGiUlbEQ,13339
|
166
176
|
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
167
177
|
sglang/srt/layers/communicator.py,sha256=NYP2IGKs5eK4X9DNG0MBbKShI1fmT2TExOOuCXR8Nlc,24111
|
168
|
-
sglang/srt/layers/dp_attention.py,sha256=
|
178
|
+
sglang/srt/layers/dp_attention.py,sha256=4QiE0Bmmafmb74IsD_URgxexq98iOuGOfgRacBrks8U,15929
|
169
179
|
sglang/srt/layers/elementwise.py,sha256=PjYv7Sk-zKbG9WiGlYDKsxvNrnxT2N1Q8bA2BWvA1Uo,18771
|
170
180
|
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=hnVVS_VsWukTYhREubWs2KcJ1GjVMEI9ECqxqOMXZv8,6729
|
171
|
-
sglang/srt/layers/layernorm.py,sha256=
|
172
|
-
sglang/srt/layers/linear.py,sha256=
|
173
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
181
|
+
sglang/srt/layers/layernorm.py,sha256=kPWECOKd8nib3JjbXNIWaCerJdvnbrz3eIpshr5KlrY,11210
|
182
|
+
sglang/srt/layers/linear.py,sha256=2qsDMtoSJbght9SQLg6jzC6eEKK5NxyzL7w5aJN1WeA,54868
|
183
|
+
sglang/srt/layers/logits_processor.py,sha256=lwB-toJFaIumzDi3OamMfv2nmPxfTibfJYNf0uDsngs,27511
|
174
184
|
sglang/srt/layers/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
175
185
|
sglang/srt/layers/multimodal.py,sha256=vNswe0J0maeBiN8ehlmxfs-YYlrmMllYl6Nc_Y57Neg,5114
|
176
186
|
sglang/srt/layers/parameter.py,sha256=jCg0G-12GZqTa9gGOqEtVCsnnuBGnYg0VmF6pc6oCFg,17455
|
@@ -178,58 +188,77 @@ sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3
|
|
178
188
|
sglang/srt/layers/radix_attention.py,sha256=MpugwaqiY2zPTeg7FVW41OljljCXmYVvHZ2MvneF6PI,3745
|
179
189
|
sglang/srt/layers/rocm_linear_utils.py,sha256=7PPh-5H2IYjiLp_g_szzVBsmiMacZ1RtjVtjdrdFJKI,1374
|
180
190
|
sglang/srt/layers/rotary_embedding.py,sha256=0SzOf8SnUbYNxeFLH5tIGuK_Hv0rRONRhRPGZLduxh8,73462
|
181
|
-
sglang/srt/layers/sampler.py,sha256=
|
191
|
+
sglang/srt/layers/sampler.py,sha256=Yr3iWoRk-eVynxfbeTlPGpn-lAjwA1ZtvHusXMsT1n0,17617
|
182
192
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
183
193
|
sglang/srt/layers/utils.py,sha256=E7PHisGiD9ZmLS4RWqCUZWxAQJbfc0WaTfRZ37gUlPI,1077
|
184
194
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=x0421kNUgnAb5LnkJR6O67vGZ0ikSD-ThluV3QGsZ_8,22673
|
185
195
|
sglang/srt/layers/attention/aiter_backend.py,sha256=WUOf8qba_wD7OgoJMKIsXR6_VdZD18alB3FajafBGSc,43887
|
186
|
-
sglang/srt/layers/attention/ascend_backend.py,sha256=
|
196
|
+
sglang/srt/layers/attention/ascend_backend.py,sha256=eu8QCXFxVRdArBlVWP3mgaFUC0by27qavEw2NU8djSY,23710
|
187
197
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=_vM05ddWy6SaoqWYPR8w5lflSE4MhcVFR271Q9EKK8E,3600
|
188
198
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=PB5BjbJHhmTg_t0kXfarTI6C3pPvKhBAqvCSGGajou0,9846
|
189
199
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
190
200
|
sglang/srt/layers/attention/dual_chunk_flashattention_backend.py,sha256=hCATQEhBATZpPhBMF-cCM9r6nxXA0dr3jOT_hTFS_T0,68656
|
191
201
|
sglang/srt/layers/attention/flashattention_backend.py,sha256=3Jgapx8tVh2PbPVi6e5TX6eBttdOSm2V53TDbZRixr8,103779
|
192
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
193
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
202
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=gDfKYL_xuiPhDakjboqGsMcDnf9Tqu41HNxmfTvUaHA,54407
|
203
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=uhltlfRQo3jQEeps2O7X7PHjpb0V_c1OejXTQ5jWeWU,39769
|
194
204
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=5iSic5ho-lkXNas9mR3uLbXbEl-do31gc8gjR7-a79k,20711
|
195
|
-
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=
|
196
|
-
sglang/srt/layers/attention/
|
205
|
+
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=WVC0VOGyVxq3AH-a6gOScfNpijIgxaEOVo5NQLEH5Xo,4823
|
206
|
+
sglang/srt/layers/attention/hybrid_linear_attn_backend.py,sha256=Vap1_eLuxiOXV1DXFGFV_TNrfv83bm9OaFmTGdQhiXI,21996
|
207
|
+
sglang/srt/layers/attention/intel_amx_backend.py,sha256=IU_E7HkPrBLfNG2ArhI1ozHZ_pROujUzdI6g2JuToL0,4154
|
197
208
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
198
209
|
sglang/srt/layers/attention/tbo_backend.py,sha256=CBnSDUmDvT-Tbhi9NHNo1LLkgUAcIsWMJgKa-sAIKW8,9318
|
199
|
-
sglang/srt/layers/attention/torch_native_backend.py,sha256=
|
200
|
-
sglang/srt/layers/attention/triton_backend.py,sha256=
|
210
|
+
sglang/srt/layers/attention/torch_native_backend.py,sha256=NdWD2ArmS1lQN9mZIbS2rcHueBWColNxvhcLaQGAKGQ,9728
|
211
|
+
sglang/srt/layers/attention/triton_backend.py,sha256=PqdGq8ifV-F0Zn3KGAVggeZn13fNiF_VBkNs4GYxg2U,42560
|
201
212
|
sglang/srt/layers/attention/trtllm_mha_backend.py,sha256=8MxCAzqsNuvO3mhFqTMXCJ0Tt0_82kFbBHie6m0ieDA,27588
|
202
|
-
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=
|
213
|
+
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=O_cgZtohn5JRW9dF2tFa14Yv55oUjTX3PUJWylCfjVA,23504
|
203
214
|
sglang/srt/layers/attention/utils.py,sha256=lx_jNw2VwlBe2VnDb1eXRRdN9WArw9rdWHTHqndUEFk,3174
|
204
215
|
sglang/srt/layers/attention/vision.py,sha256=PZUJuswPWvJ34NTtxJkcXnusojDv0pO0UhrsjL4SWYU,20268
|
205
216
|
sglang/srt/layers/attention/vision_utils.py,sha256=6hPPAt8p3SOm7tgHNUesnMLxvQiKbaOM5EK6K-ig5dI,2771
|
206
217
|
sglang/srt/layers/attention/wave_backend.py,sha256=_rjyALSl5huNtIGSe6OJlBrC04LhwBBu62bgjlkavkw,23010
|
218
|
+
sglang/srt/layers/attention/fla/chunk.py,sha256=N8ToAspPlgR7sVJBImzpmlGV6rWsMA7aTaTa1iddcPg,8929
|
219
|
+
sglang/srt/layers/attention/fla/chunk_delta_h.py,sha256=Gf8RgLesGaR9GM4HTB7kDDCVirwR9XvO7O3I1HWdcuY,10681
|
220
|
+
sglang/srt/layers/attention/fla/chunk_o.py,sha256=IZllM88Ap1ztEF9nOSfcx7KmRvmwIwiBMqwT9AjjH-U,4980
|
221
|
+
sglang/srt/layers/attention/fla/chunk_scaled_dot_kkt.py,sha256=wipJDfcYGxMjYiLdoa2z_lyKTd9RVwkacWjIKRFIN1Q,4411
|
222
|
+
sglang/srt/layers/attention/fla/cumsum.py,sha256=beIT2WTSn8Wk_wknoWM3JYQhzmzR1JJwMFzspsXvWng,8374
|
223
|
+
sglang/srt/layers/attention/fla/fused_recurrent.py,sha256=DzMBjjy4owkeqZx98U9OiJEr6ZgzX6guPe-FOAHKNm4,20856
|
224
|
+
sglang/srt/layers/attention/fla/fused_sigmoid_gating_recurrent.py,sha256=rj9exYjnuzLC7xzmse5yGQrp43yJVs5clr_WhSf4eR0,6424
|
225
|
+
sglang/srt/layers/attention/fla/index.py,sha256=kQGcR1doARV324QuA-faNoyo6u8a_wb-DfiPe_bOdhY,1050
|
226
|
+
sglang/srt/layers/attention/fla/l2norm.py,sha256=XOs5nGdWROp3FW4fHSObC8sa_x697yDV0jt5UKuLllE,3783
|
227
|
+
sglang/srt/layers/attention/fla/layernorm_gated.py,sha256=gNAAUyRfnjf5vTx92Gkah5UeumrlgH7oCq0Tg5D_5mQ,9938
|
228
|
+
sglang/srt/layers/attention/fla/op.py,sha256=Qc-zHwZY9-8Aw53AuuzNfpbPBwKgIvVMgtWcfJLl6A4,1695
|
229
|
+
sglang/srt/layers/attention/fla/solve_tril.py,sha256=-Z51hFsLER_Lzn8h21WRUajbVOA1wuu5TSEvaC2AvK8,14405
|
230
|
+
sglang/srt/layers/attention/fla/utils.py,sha256=yBYjW-blAsq_uZxZ961Dub3cUouIvl4DCKV9UqkQSJw,10474
|
231
|
+
sglang/srt/layers/attention/fla/wy_fast.py,sha256=zf6_76vq7yYtn9Ir1Le4RVOKLaPNF_4bNST3ePuH0cU,4407
|
232
|
+
sglang/srt/layers/attention/mamba/causal_conv1d.py,sha256=7NaZVlsSBjvNFP92cn1U11JL8vTuaq0HiyTybDHwOlo,4460
|
233
|
+
sglang/srt/layers/attention/mamba/causal_conv1d_triton.py,sha256=WgkBUew5PVMH9lRPA-mbBpCW_94d30NvuKGHRLes58A,40810
|
234
|
+
sglang/srt/layers/attention/mamba/mamba.py,sha256=lgVITKk4QFJQEsGN2p1a5RDG4bxGwqT0_K_hrK-5Dbw,2489
|
207
235
|
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=JnOtqtPXEgn_T0R4gGCROx1szlAhu_G_ODNKCazz0lE,20554
|
208
236
|
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
209
237
|
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=eYg4xQoH5gBkM7bjzpBIpTdcelvUK3BujJ-8eXRCm70,17108
|
210
238
|
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
211
239
|
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
212
240
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
213
|
-
sglang/srt/layers/attention/wave_ops/decode_attention.py,sha256=
|
214
|
-
sglang/srt/layers/attention/wave_ops/extend_attention.py,sha256=
|
241
|
+
sglang/srt/layers/attention/wave_ops/decode_attention.py,sha256=oJNBG57cySgxtmJe1MSEsZKOIQOXnH0iVAcFO6DUWvY,4732
|
242
|
+
sglang/srt/layers/attention/wave_ops/extend_attention.py,sha256=LyZQQIvFYfcIcObgy_tETK5JxRLgAkOYlF-KhGcGEoA,3877
|
215
243
|
sglang/srt/layers/attention/wave_ops/prefill_attention.py,sha256=viTUit0rxjVV5UahuwmVAhmL66YRFJD4g1YhH_oRBu8,2344
|
216
|
-
sglang/srt/layers/moe/__init__.py,sha256=
|
244
|
+
sglang/srt/layers/moe/__init__.py,sha256=P8OC-pUE5yeEr80QUDqSPwF9a9BAYPuaK7GNlQovsJw,863
|
217
245
|
sglang/srt/layers/moe/cutlass_moe.py,sha256=JKJED-4709ndP5AwhQ7Vi04GJjw5d9Xl_mWOsZPZ3U4,14298
|
218
246
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
219
|
-
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=
|
220
|
-
sglang/srt/layers/moe/
|
247
|
+
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=psvH2RhUQkK4oyaSE7xe0EncCqLvNbd_NwR4XHxk79w,7017
|
248
|
+
sglang/srt/layers/moe/flashinfer_cutedsl_moe.py,sha256=rHy_wd-M_6nuOyOm7bJiVTH4QylrKtjWjhE0x4AEqts,5057
|
249
|
+
sglang/srt/layers/moe/fused_moe_native.py,sha256=XzJPM9Z6YQ4ejrMrBFt3l1i7guBcdQTXo9-gT5H8AIA,3479
|
221
250
|
sglang/srt/layers/moe/rocm_moe_utils.py,sha256=07Z99bTV3B-b2Cbm-odhGpx2twxtnVpYvaDMBE1K3LM,4555
|
222
251
|
sglang/srt/layers/moe/router.py,sha256=eUNu_Uz5VB2FOZzZyYuZo5pokCVBS17_fcjHQbmvDSE,12181
|
223
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
224
|
-
sglang/srt/layers/moe/utils.py,sha256=
|
252
|
+
sglang/srt/layers/moe/topk.py,sha256=HcvKwbew1W4NJ-IGCp2aietW3o3KQPRuC7siRrjavt4,32240
|
253
|
+
sglang/srt/layers/moe/utils.py,sha256=GaVPzQAGvgrVQddTQAFxn7IzQ2me78C2V59RTwapD7E,6090
|
225
254
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
226
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
227
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
255
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=poGKusUolwN3cVkX2ZpJlvz9L2q3dURenPuMxgz1XM4,46159
|
256
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=9YLvJeMzDYhAT1DUSaWANoF4OwyjV9YlwD8ODI80Bow,32205
|
228
257
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=tis0ZJmih7gKHCurbLtY_o-bY3K4MOzQLYLC3ftIOf0,977
|
229
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
230
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py,sha256=
|
231
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py,sha256=
|
232
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
258
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=mKH6zTTuh_Z8Ceg6d1VWjGBI3iPBn1YfGO6udxIRAtU,23306
|
259
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py,sha256=VXVU_7cOxtSi4WcVezbvYmYSYdmQ6TcjoxPb5cKmreM,7696
|
260
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py,sha256=QOdl5uhZ8--aryXnKObdspKonGcF6Tc_U9o_lC_opo8,27760
|
261
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=02RJNoGXz5nlujGgpQZ5G0_D1ZKJjBzpBJHIYyOzYJw,39676
|
233
262
|
sglang/srt/layers/moe/fused_moe_triton/moe_align_block_size.py,sha256=U93mxPPU2RP7d3QRSvoG3OCtUQIK8YhQfHf1ZGeREmY,3284
|
234
263
|
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk0nPWQelgvi1rV9Z72FetRo6p7E3rsYs,10986
|
235
264
|
"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
|
@@ -398,6 +427,7 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
398
427
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=352,device_name=NVIDIA_RTX_6000_Ada_Generation,dtype=fp8_w8a8.json",sha256=RMYwqtB7hYeaCyuZ1feVnRhBGlN4jMcmNQX2hqUqBlk,3254
|
399
428
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=LNx1W_BsWZcpHomiScCRap46dV0-F7S_w3Htskoqlm8,3263
|
400
429
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=qc7qnAk3BYcP5m_eT8IPDfnvFrng_kiRCS36_Uy1M2o,3260
|
430
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=JfLZHVC84ZsHVIdhJ2jGT9r2ZqGGxBqIZx4HRjFc4n4,3254
|
401
431
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=768,device_name=NVIDIA_H20.json",sha256=T2sNHVZCLbyuO68ZeudUzQMBsAQzs2-eo53I-EUIuWM,3233
|
402
432
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=rqPWpRfa9s7USa9cUyHAVP50WYkCqXDJzfKZhqk6GHw,3267
|
403
433
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=320,device_name=NVIDIA_H20-3e.json",sha256=cWkEpNqnyn0QS8HcgWiwWI1xqh_U93_S1kyNeb69aOc,3238
|
@@ -415,58 +445,68 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
415
445
|
"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
|
416
446
|
"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
|
417
447
|
"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
|
448
|
+
"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
|
418
449
|
"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
|
419
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=dPe_9-JH0wF8q7Mhec4WWSLSGRE2gj_AQT3dnR3FREI,3257
|
420
450
|
"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
|
421
451
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Max-Q_Workstation_Edition,dtype=fp8_w8a8.json",sha256=RMYwqtB7hYeaCyuZ1feVnRhBGlN4jMcmNQX2hqUqBlk,3254
|
422
452
|
"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
|
423
453
|
"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
|
424
454
|
"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
|
455
|
+
"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
|
425
456
|
"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
|
426
457
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=64,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=QEk8bE-GieZltTiv3ig__ScM9Q_4K-c75UzIuDrGmPA,3232
|
427
458
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=FEnjuvvky-cvW1iq8TPrfGOOH8y4rOEx4jlYZ4tqbDs,3253
|
428
|
-
sglang/srt/layers/moe/
|
429
|
-
sglang/srt/layers/moe/
|
430
|
-
sglang/srt/layers/moe/
|
431
|
-
sglang/srt/layers/moe/
|
432
|
-
sglang/srt/layers/moe/
|
433
|
-
sglang/srt/layers/moe/
|
459
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=JUzq6vJzOAVw3VOXzCjBpaLpf5OxPQmo2iJPJjzMm6o,3241
|
460
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H20-3e.json",sha256=arTXsLka4xWkCERNBayRHqfhwrtqdd_Yhy-SziVVTZY,3230
|
461
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H200.json",sha256=HRGJWqy1CC7ouRY6e_t3C832CM0BIlQ0Zo6nofzBf8k,3238
|
462
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=256,device_name=NVIDIA_H20-3e.json",sha256=3oOQFsbOjejH_zQaMYlKUtQ6SnxIH5_f3UIaFfSlc8U,3236
|
463
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=256,device_name=NVIDIA_H200.json",sha256=mmiNUNFajlYSjFXL0DMykS6I-D1P8AQXdRBpeCARD-0,3243
|
464
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=64,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=FeRAKkFUl3iMlNBBrb_Yoe4OsWyvSbVt5-wmXEjLbFQ,3237
|
465
|
+
"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
|
466
|
+
sglang/srt/layers/moe/moe_runner/__init__.py,sha256=Dc4PH6HfzQDjJWL7iuZ-0qh8oRu7OtnH6IEl675pYiU,172
|
467
|
+
sglang/srt/layers/moe/moe_runner/base.py,sha256=GMdFI74BGO5HDjtel5QWI7W4CFix0BHkw_HrjVswhcw,8905
|
468
|
+
sglang/srt/layers/moe/moe_runner/runner.py,sha256=7ZOqDu0r1GY-9ra1VICq4WmH1nJVSQoE5yBXuSUr2CI,2669
|
469
|
+
sglang/srt/layers/moe/moe_runner/triton.py,sha256=YaPqGIX-5y25nxmjF54_ASYbr9Dw4RYze2cNV4cUg-Q,14433
|
470
|
+
sglang/srt/layers/moe/token_dispatcher/__init__.py,sha256=I5I1ySCHbyAW5cFQy9mpuqkSWqLclLmi2AspCkoP8ig,993
|
471
|
+
sglang/srt/layers/moe/token_dispatcher/base.py,sha256=BqqwuSETP47vTaHkUoQWTEeZcAkg0n_Dgka-PkFM4uc,4029
|
472
|
+
sglang/srt/layers/moe/token_dispatcher/deepep.py,sha256=Hm8qcC5Z7hfT9PfNFxQb-8uw3qe47O30s2kxoGcpi0g,23740
|
473
|
+
sglang/srt/layers/moe/token_dispatcher/standard.py,sha256=_OSudEOHA5qHqR5TJqnylQxUYyk7ZnhRMGOf7sMCyt0,1526
|
434
474
|
sglang/srt/layers/quantization/__init__.py,sha256=GmJvVSlkJXf2AmTfWBN6EBrOhhYlxPYNE_eAEXMZfjs,7813
|
435
|
-
sglang/srt/layers/quantization/awq.py,sha256
|
475
|
+
sglang/srt/layers/quantization/awq.py,sha256=YuAkweqSvQQGTGQvg4VpNXevSaJvT8CROpiNzmY_3tQ,26980
|
436
476
|
sglang/srt/layers/quantization/awq_triton.py,sha256=4XwJbRNlFmlvjbMGtWF1Wvk26Kf96162vNEmuI5Kars,11737
|
437
|
-
sglang/srt/layers/quantization/base_config.py,sha256=
|
438
|
-
sglang/srt/layers/quantization/blockwise_int8.py,sha256=
|
439
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
477
|
+
sglang/srt/layers/quantization/base_config.py,sha256=ql3kwwnjVzZGh8BUcimMt8K6kFxQtVbR5WgZHXqkOqA,7245
|
478
|
+
sglang/srt/layers/quantization/blockwise_int8.py,sha256=pqSLo4gwazZ4ajdVzyouwh_Z5oVDbWq9wo8RnrMdY8o,13998
|
479
|
+
sglang/srt/layers/quantization/fp8.py,sha256=1Te5ft-yBXgvdcYcJ4LiBcLpukNqizjuUz_02cUxauU,50783
|
440
480
|
sglang/srt/layers/quantization/fp8_kernel.py,sha256=Mgigb6GmF66oCrgjS97IvDDSacNYb0u-VYAf4FChhqM,54849
|
441
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=
|
481
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=MfGS-m3g-p33YvvkUO052d9pilOR-bTmIND3SIhYUHM,29195
|
442
482
|
sglang/srt/layers/quantization/fpgemm_fp8.py,sha256=dq7rJz-QB9LovmZZLBMK8YJEOr05wjVrtWLmSTkXjYw,7004
|
443
|
-
sglang/srt/layers/quantization/gptq.py,sha256=
|
483
|
+
sglang/srt/layers/quantization/gptq.py,sha256=Qe6XfBWd9aOW7jkLmQR61AjmJRe5MJi6FJvGno1HH4k,39433
|
444
484
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
445
485
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
446
486
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
447
487
|
sglang/srt/layers/quantization/marlin_utils.py,sha256=aM3GU7b7rHNZE-tZjRSrtOaPWzSaMcLxck4he8MlEVI,26344
|
448
488
|
sglang/srt/layers/quantization/marlin_utils_fp8.py,sha256=iSjq-ikPOTU5plrWNTW4MletKLySIrNl5NhQmY6FyAo,12508
|
449
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
450
|
-
sglang/srt/layers/quantization/moe_wna16.py,sha256=
|
451
|
-
sglang/srt/layers/quantization/mxfp4.py,sha256=
|
489
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=CYesMhem0rT8hBTRoo8SxOByYHQqT7kEypE46R-WA1k,58024
|
490
|
+
sglang/srt/layers/quantization/moe_wna16.py,sha256=uoRhxJ8W_U_VFpbn03YEp0aCjbzqquWwonjuN7KBucw,19117
|
491
|
+
sglang/srt/layers/quantization/mxfp4.py,sha256=i-QaMdDp-tlHdwrmgGiLmzgzNk_xZ3GxivLFa0GcdgY,32708
|
452
492
|
sglang/srt/layers/quantization/mxfp4_tensor.py,sha256=bGeCXlIOhmFZFGWp_lITkIRDEgGUaLpawDvMy1cTOmA,5389
|
453
493
|
sglang/srt/layers/quantization/petit.py,sha256=74Jn0eICq23v_b4rEctDaYTINtbqkdM6IXycT-_FbbI,8954
|
454
494
|
sglang/srt/layers/quantization/petit_utils.py,sha256=-gy4zMhqNoIA1R0n7-5C0efV54jHonCUgPDUUFjGsyM,3245
|
455
495
|
sglang/srt/layers/quantization/qoq.py,sha256=jM96uJfKz3vo1B6SSIrQXNT3vnD3UJrepK2eY-tSQU4,8139
|
456
496
|
sglang/srt/layers/quantization/rocm_mxfp4_utils.py,sha256=Z4pYWl6ExOXq2qfTHorW16hVbJ-Rk4G8Wrxn_x8boHE,327
|
457
|
-
sglang/srt/layers/quantization/unquant.py,sha256=
|
497
|
+
sglang/srt/layers/quantization/unquant.py,sha256=T8w0mPvtBM1JhGhle6NoDY9C4xfmPWHU_VEJZWSnUNY,16079
|
458
498
|
sglang/srt/layers/quantization/utils.py,sha256=d4eaS4-Z4q3GRgb4HDMr2EoWEdQCefrVdJufK6n_NQY,18509
|
459
|
-
sglang/srt/layers/quantization/w4afp8.py,sha256=
|
460
|
-
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=
|
461
|
-
sglang/srt/layers/quantization/w8a8_int8.py,sha256=
|
499
|
+
sglang/srt/layers/quantization/w4afp8.py,sha256=WHxSd_cN9xPLjrUywrCsUBHzfAmjDQOHgCVvh8DkPJk,12256
|
500
|
+
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=ugLV4G4MDog-UuLqSnEasBqE3Hh6AqE5ZYI371ean90,10415
|
501
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=ChRre9mx8GHQ_EM7pnUdgiMsw6pVPCrAMYGS5ANGuuU,36645
|
462
502
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
463
503
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=DsPCI82A4rqI6mjKo-WorIKUweppFV7-16Qku-zW9_g,25897
|
464
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
504
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=tFw8PIF5r8yjdJFt2_3Ou72vUJvgLd3bXFOWdgsCeno,26732
|
465
505
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
466
506
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
467
507
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
468
508
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=VvqVpAr66AlS5IPVuIR5Nu0ESH0oAoKo545jNart6lI,5493
|
469
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=
|
509
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=4cfB6pv7kt8Ek0e88vLyXymSW6VqbAUpIjNt_-KK9-M,6318
|
470
510
|
"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
|
471
511
|
"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
|
472
512
|
"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
|
@@ -622,90 +662,100 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
622
662
|
sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
623
663
|
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=PI9r3PHCMK9EgpoFuBgR4jvokA5sBz8zyC47ps3wet4,8164
|
624
664
|
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=8C4xyO58N3Zl8h-fYddUpXDs3mnSqjYbaLt12cPB2XA,778
|
625
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=
|
665
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=qiUuQn-InDLYVNDPFOxde2XB-qlE0fol0HPTkY5KN8g,3197
|
626
666
|
sglang/srt/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
627
667
|
sglang/srt/layers/quantization/quark/quark.py,sha256=EqQvWzAc6nd_yl6UIMIwmozKif4I8fRNfBum040UUEQ,14613
|
628
|
-
sglang/srt/layers/quantization/quark/quark_moe.py,sha256=
|
668
|
+
sglang/srt/layers/quantization/quark/quark_moe.py,sha256=e2bVOYrdc7Tlko_B3XucXih-ZGHLgbgyg8oxJWsMEBE,6982
|
629
669
|
sglang/srt/layers/quantization/quark/utils.py,sha256=zZHRe9mjxGp16_OJ5Qy_UtnQgipl3ZRZUmruYvyEm_w,7445
|
630
670
|
sglang/srt/layers/quantization/quark/schemes/__init__.py,sha256=z1LHBPqkxAS6Wp70DWwESOSixWpIhIQwz1IHcWDdURQ,167
|
631
671
|
sglang/srt/layers/quantization/quark/schemes/quark_scheme.py,sha256=b8-Djo-UQAwgxSWViKDoEP5dOSesnEBPyozX-osB3WY,1478
|
632
672
|
sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=sW57dU7HoxQGVbzUhyhRirGWA8oVpENB4NTzO7URGgU,4198
|
633
|
-
sglang/srt/lora/layers.py,sha256=
|
634
|
-
sglang/srt/lora/lora.py,sha256=
|
673
|
+
sglang/srt/lora/layers.py,sha256=0XlVcBTT1InMsBoLfiOO7yOnlDrnpXD_08wKo84T4B4,11852
|
674
|
+
sglang/srt/lora/lora.py,sha256=2PaloPsDIYT5f7alwWEpEMY6H4lOnSprc7Qp3f0KrS0,7554
|
635
675
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
636
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
676
|
+
sglang/srt/lora/lora_manager.py,sha256=A5eXAik7_7Xs_THp5T21ft7gCvUXVVZtJXd7qdrqUL4,18811
|
637
677
|
sglang/srt/lora/lora_registry.py,sha256=osbau-sQZ7BuCeGGpBMFy4w40GO5FGqRgRwDyxxgNmg,8167
|
638
|
-
sglang/srt/lora/mem_pool.py,sha256=
|
639
|
-
sglang/srt/lora/utils.py,sha256=
|
640
|
-
sglang/srt/lora/backend/base_backend.py,sha256=
|
641
|
-
sglang/srt/lora/backend/triton_backend.py,sha256=
|
678
|
+
sglang/srt/lora/mem_pool.py,sha256=KrjMo91sU_SVF9hLHlgzYTVR6KAtOPGzey3CMKL3tkU,11479
|
679
|
+
sglang/srt/lora/utils.py,sha256=_nyVUkH23v38vaMjZoORFfJtD02iCKaHr3rrNUOXezo,4263
|
680
|
+
sglang/srt/lora/backend/base_backend.py,sha256=e88u2MgQ1wE4VoZHyvtnvXsiSYczPyQq3Uiyi0Yn8p4,6145
|
681
|
+
sglang/srt/lora/backend/triton_backend.py,sha256=xX6H5yaTynQ64ipkmU1987vz5u8_ompaAjXdLSB4AbI,5974
|
642
682
|
sglang/srt/lora/triton_ops/__init__.py,sha256=JGOYPIn1XbGcyJTbt8A0qoc02PYONSGNNjGkC8yJpAM,283
|
643
683
|
sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=QURCYxHNR8Ls4SQtt3dvdgjvdDVhywI9tOzsK8SV9m8,5779
|
644
684
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=z9BB84Xu_MjwCu5v9Yvji-FkIzfEjDySAFybc4WYv7A,6483
|
645
685
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=Ksova04wgeGsFqGOXWqJtMYaHgyUYcx8VU42BZQOkVA,5129
|
646
686
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=VqCAFvUtq_l-0RGIkx3W_fzD55QcW2FAcqpvSHOBFp4,5115
|
647
|
-
sglang/srt/managers/
|
687
|
+
sglang/srt/managers/async_dynamic_batch_tokenizer.py,sha256=btIWhI15a3QCLabdZZhrJVEWZ3zZTgldbv7pGjAPZqo,7236
|
688
|
+
sglang/srt/managers/cache_controller.py,sha256=wNhN1oSUObmJzGqvQzzZneUB-3b0ld1DHt3NEkzv8G8,33497
|
648
689
|
sglang/srt/managers/configure_logging.py,sha256=8sNXZ2z9pBWOwn-X3wyz013Ob8Nbm1zDxRkxoZjH-l4,1633
|
649
|
-
sglang/srt/managers/data_parallel_controller.py,sha256=
|
650
|
-
sglang/srt/managers/detokenizer_manager.py,sha256=
|
651
|
-
sglang/srt/managers/
|
652
|
-
sglang/srt/managers/
|
653
|
-
sglang/srt/managers/
|
690
|
+
sglang/srt/managers/data_parallel_controller.py,sha256=ov8R40V3LbdRgX60ypr9oRD3mNy_paKurokTLDPPkvE,16539
|
691
|
+
sglang/srt/managers/detokenizer_manager.py,sha256=vIW-chLWyLJrUL0i91l1cINvfx5W4zfXbR79t2n-mM4,11779
|
692
|
+
sglang/srt/managers/disagg_service.py,sha256=7VyRva5oniAPs8G-DYg2fv-mdjSxk9cLZPzl_TmB_2Q,1588
|
693
|
+
sglang/srt/managers/io_struct.py,sha256=Ra4JHCApkPh31FkkMhy0hi__lToHT_5VzOFDjNE0cZ4,46491
|
694
|
+
sglang/srt/managers/mm_utils.py,sha256=-gElspd-PTWx8k3uuIm83Lb8QXD_dGY5_1WDovKMBKM,29506
|
695
|
+
sglang/srt/managers/multi_tokenizer_mixin.py,sha256=sTkiPa68l-0F2Mw59yhG357y5FzRbco2hWVR6zs_25A,21755
|
654
696
|
sglang/srt/managers/multimodal_processor.py,sha256=cnWpu2G79v1a6FJB_FriLxESgGUbfC3GptLmeRVVgew,1801
|
655
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
656
|
-
sglang/srt/managers/schedule_policy.py,sha256=
|
657
|
-
sglang/srt/managers/scheduler.py,sha256=
|
697
|
+
sglang/srt/managers/schedule_batch.py,sha256=Cbj_2F9iaRdhrnI_A6wD-OX-XZfYKbscvisbg4RGPxw,78958
|
698
|
+
sglang/srt/managers/schedule_policy.py,sha256=ae3XqkItQpcBxOGaWmXRh-kqYtJRegr44SGqX74g918,22454
|
699
|
+
sglang/srt/managers/scheduler.py,sha256=P1wm2LMJDSHPtmHx5qm3gcm0NPll5KW7RtnsFEpjy0w,113409
|
658
700
|
sglang/srt/managers/scheduler_input_blocker.py,sha256=zP8xU_UmU2H0AB6sEqvivDcDB1QDgTauNDYDIJ7Nez4,3683
|
659
|
-
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=
|
660
|
-
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=
|
661
|
-
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=
|
701
|
+
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=EjWS4Sydnx-3LpOGK1MmMMe90ujfOQ6KZ5XvHzBIzYE,14678
|
702
|
+
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=EciJkOVhneS5czgiEdOC8tjxyLJP5Xll9VCjF1XzJ6k,33365
|
703
|
+
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=4-slXlOPo8AMD8nkvASmA2hov_-dX2a2CvVd0AKFTTM,11403
|
662
704
|
sglang/srt/managers/scheduler_recv_skipper.py,sha256=8rVQCBjn9f26Th4XbeUS3fEsvo1GI029Me28wMjcKRY,1103
|
663
705
|
sglang/srt/managers/scheduler_update_weights_mixin.py,sha256=uk7Dusr8EJBDRdcuQNIoedj0oP4tmSWrUbEqmjclwnk,5813
|
664
706
|
sglang/srt/managers/session_controller.py,sha256=FGADRGSkRmS76o_BQ2fivpgw0Q5Q-K0Ws3aezH41YSc,6041
|
665
707
|
sglang/srt/managers/template_manager.py,sha256=M4EshVv1OhKxUAGQPP4OntRkSkUVvG93457xsYfWnQk,11968
|
666
|
-
sglang/srt/managers/
|
667
|
-
sglang/srt/managers/
|
668
|
-
sglang/srt/managers/
|
708
|
+
sglang/srt/managers/tokenizer_communicator_mixin.py,sha256=zSMohjUKq0wzNOP_TTDf8HHZGZB5Ii51y9Kloq6rg6M,21296
|
709
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=ZWL_oEXZEtuxCDEIRk-N2JdFYqH7eFsSG_a5dxl1PQI,79576
|
710
|
+
sglang/srt/managers/tp_worker.py,sha256=U6feflbrsvtqXOnLg0cvYj23FCT2WhkYtEi2Oz6-ghs,13847
|
711
|
+
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=eFONCub_5cEsNAyqVwxsa2ui5hAoHLYik43hU7kvCcA,12095
|
669
712
|
sglang/srt/managers/utils.py,sha256=WbUdADEdiSOoQNfwjfU64mNaXoskEveBO1HP_t0FJtQ,5687
|
670
713
|
sglang/srt/mem_cache/allocator.py,sha256=47M3lrAv9k2MJXQc82oGXokLb_3u1A8LFNL9WmgIBN8,18219
|
671
714
|
sglang/srt/mem_cache/allocator_ascend.py,sha256=i0KPCcFlzGkCIjW8ph3IPkBXAWTqq4-AeaoG1wR--lw,4471
|
672
715
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=hLS2ncTMAz7Kpdk5pNwn5c6g8b61_K9OCBL4Vj1xsYc,2801
|
673
716
|
sglang/srt/mem_cache/chunk_cache.py,sha256=jbJeEEZ5_WYEF_AnDZIAu2sMD4hAGAd_24F980fjVwU,3199
|
674
717
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
675
|
-
sglang/srt/mem_cache/hicache_storage.py,sha256=
|
676
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
718
|
+
sglang/srt/mem_cache/hicache_storage.py,sha256=o9__S2_pH6FZOXUMvDbKSxzuCzFZd7SnBPlU92YIIWY,6990
|
719
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=96t0FUcrjee8ScjxFXmw_SXAjB90vxo0LvPvzEBgSB0,31913
|
677
720
|
sglang/srt/mem_cache/lora_radix_cache.py,sha256=4NbK0Rc15kTiCOSsthyM6WsZarMK2MNhtsNqYMakJ5k,14369
|
678
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
679
|
-
sglang/srt/mem_cache/memory_pool_host.py,sha256=
|
721
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=ggGjnQy_i2qUNH7BDSe_J1Pp8O5QA5X8k8cHP7G6XG8,50515
|
722
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=ihcD2qmBEJayhyxYVw5z6U0T1J-RbSEqPkolC-CGRxo,28978
|
680
723
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=zPnQLQhBZ6zsUpCQPSoNkrB9EEvpoDQS4mU7c3sRWjE,2171
|
681
|
-
sglang/srt/mem_cache/radix_cache.py,sha256=
|
724
|
+
sglang/srt/mem_cache/radix_cache.py,sha256=WrzDSfUdyctshXQ1hN3LKpH-DCY2-dZ8xzmc2Iy6jeE,19027
|
682
725
|
sglang/srt/mem_cache/radix_cache_cpp.py,sha256=YuYt4xNzfmNNSkwaAk3VLWcZI74_XQobIyEgt96f7Qs,9284
|
683
|
-
sglang/srt/mem_cache/swa_radix_cache.py,sha256=
|
726
|
+
sglang/srt/mem_cache/swa_radix_cache.py,sha256=m0MAXw8bpY4nRWvU4qEWR8UzjgoqrYZSsy4aF5fWsKw,40226
|
684
727
|
sglang/srt/mem_cache/cpp_radix_tree/radix_tree.py,sha256=tQZpz-H6HxNAQe9mYqt6aX8mfDZyu_fbJTcCNK-Ns1M,7179
|
685
|
-
sglang/srt/mem_cache/storage/hf3fs/
|
728
|
+
sglang/srt/mem_cache/storage/hf3fs/hf3fs_client.py,sha256=le_iTE5HZAbQNToa5E_dq_3U5ztu60ej-58tmzRtndM,5245
|
729
|
+
sglang/srt/mem_cache/storage/hf3fs/hf3fs_usrbio_client.py,sha256=6oH4v_WF_pKH4FMSr252v6QPhBCnRHztHqzuS8j6_QI,5323
|
686
730
|
sglang/srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp,sha256=dDYPtxmL6OFhEyv_GuTgzkTDpBjcD0EK8kphnn7eaGc,1133
|
687
731
|
sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py,sha256=lJ9Jp2kOgQQaUihxlO9l-W8fYfOMa1h1y0WAtzzFGLM,17850
|
688
|
-
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=
|
732
|
+
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=ujsS5VMF8hZtlJDk3ye0atstEcyhPoN8vHnMYCDnAgk,17977
|
689
733
|
sglang/srt/mem_cache/storage/hf3fs/test_hf3fs_utils.py,sha256=g2h0Woa2CK39pRTigHCVR_hq095dTaC70lCIAIs9THM,1089
|
690
|
-
sglang/srt/mem_cache/storage/
|
734
|
+
sglang/srt/mem_cache/storage/lmcache/lmc_radix_cache.py,sha256=2G9qyIiQbBaDanAFQEL_2-DoQA7F-B_rVP3INXCXb0E,9764
|
735
|
+
sglang/srt/mem_cache/storage/lmcache/unit_test.py,sha256=DCSZDMJAe-HehL9hWzsP759pck36Q-8ijxWZKfgXmA8,3590
|
736
|
+
sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py,sha256=Lu-OfJW4aV8FYq0BB7nC-0VN713TlGK4RkeyeekHzL8,12505
|
691
737
|
sglang/srt/mem_cache/storage/mooncake_store/test_mooncake_store.py,sha256=6TiqbzEIL71DC7wL1B-Q-SMMZRYsz08sg-dZYeMzmAc,4930
|
692
738
|
sglang/srt/mem_cache/storage/nixl/hicache_nixl.py,sha256=bau9Jsp50lpEiy_osgb-dYzeoUkPWM03x7Q8z2BpKaU,9920
|
693
739
|
sglang/srt/mem_cache/storage/nixl/nixl_utils.py,sha256=KXkwMrbWwIOUOASINnUo4HyheiMd-93smmwGLv0CacU,7463
|
694
740
|
sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py,sha256=vENVvGAd3PqcQEFA812wPoSBYhRemLr8Sfh1LQa0INU,9609
|
695
|
-
sglang/srt/metrics/collector.py,sha256=
|
741
|
+
sglang/srt/metrics/collector.py,sha256=frwLXOLFwqpWmJ1bVg4wKOclF9DYaX04dqo6Fs-leek,35165
|
696
742
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
743
|
+
sglang/srt/metrics/startup_func_log_and_timer.py,sha256=PRVg3Z2d5GBMFifZXR-VhzGcn9nmKTkqEU41VJKZmaI,4937
|
697
744
|
sglang/srt/metrics/utils.py,sha256=BkLQFOfzNknDJ5zc4wOqkJ9awLuQE7EtwA0EYjlJg7I,1715
|
698
|
-
sglang/srt/model_executor/
|
699
|
-
sglang/srt/model_executor/
|
700
|
-
sglang/srt/model_executor/
|
745
|
+
sglang/srt/model_executor/cpu_graph_runner.py,sha256=lwh4RL4K3wPyCIz4lA_J7CtPZt4L0rxDLJcg8uNrzpc,23410
|
746
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=aOC4sKZj1wqAAVTLncRnlOsE1nujBF_z8GaUczeDt-I,34143
|
747
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=wlDLDfOjSVoafqw_OvrByAzGwqPHa8c_Xmw8sRzT8Ws,42858
|
748
|
+
sglang/srt/model_executor/model_runner.py,sha256=HxQLITAFfpEir90P2NcviCZq4rPlOV7rjo1QU-tP-bs,91828
|
701
749
|
sglang/srt/model_executor/npu_graph_runner.py,sha256=isp2Plkf4b_gdjptYxJhTJk7JL21Jg-Md3hAYIuSVxM,3424
|
702
|
-
sglang/srt/model_loader/__init__.py,sha256=
|
703
|
-
sglang/srt/model_loader/loader.py,sha256=
|
750
|
+
sglang/srt/model_loader/__init__.py,sha256=_1Y5sUZGxEEG_bmvLbSgYGa__qO60_d0blGB8sIdOgo,1020
|
751
|
+
sglang/srt/model_loader/loader.py,sha256=_w6Ir5c1h59kHZDd0cBAzO623azjsD09mwt_n3fJFvQ,64644
|
704
752
|
sglang/srt/model_loader/utils.py,sha256=KrOpyd_eefZC3zFnhnwxIKNTx9G-MmA6jIK3NQbTW0E,5002
|
705
|
-
sglang/srt/model_loader/weight_utils.py,sha256=
|
753
|
+
sglang/srt/model_loader/weight_utils.py,sha256=mv3a-c0M2ocDiwAtD6h6uvCybL5BM738te_QrbCaQa8,38611
|
754
|
+
sglang/srt/models/apertus.py,sha256=UL2Rd1TDDXPb2N4rWyymI3JThG7KlrGIyBuDIFCitPE,26002
|
706
755
|
sglang/srt/models/arcee.py,sha256=Q6fujRESEnljzs8ls3XGsPtWxzfKfUa0QAvAekYzeBY,18981
|
707
756
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
708
|
-
sglang/srt/models/bailing_moe.py,sha256=
|
757
|
+
sglang/srt/models/bailing_moe.py,sha256=LNJoYTLrkayz5v0KH2cduqCGn0NkVkQyzpbSuUIGqjY,37134
|
758
|
+
sglang/srt/models/bailing_moe_nextn.py,sha256=ntuaXP8PXc_X_oqmd4fp_FzpRmnajKoWQynXwjsEN5M,6000
|
709
759
|
sglang/srt/models/bert.py,sha256=ODJe8YfNRP-hHsomFWk4_QpcuiSsNfjzGf256EDS0Pc,15802
|
710
760
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
711
761
|
sglang/srt/models/clip.py,sha256=kOPSXnmgH_QKu2-ENn49HLDS9yf7Gm1HCOE_YvoNhlA,19858
|
@@ -714,9 +764,11 @@ sglang/srt/models/dbrx.py,sha256=117gwrB_o8VlACwDH5YlXkPfuS7t2Mh-nyJvpNpIYxs,159
|
|
714
764
|
sglang/srt/models/deepseek.py,sha256=M7nyHcAbTIs8vc1g6u00oy22-pp704Xp4T3clBzu4xM,17460
|
715
765
|
sglang/srt/models/deepseek_janus_pro.py,sha256=td8xGs6ARfJ8AQCYwUhMOZoWigrAs7m3trF5-kXCqik,70418
|
716
766
|
sglang/srt/models/deepseek_nextn.py,sha256=uoiJxAVl9DX7bQcjyuouAZz6W-cB1HMubcirTBghyR4,6115
|
717
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
767
|
+
sglang/srt/models/deepseek_v2.py,sha256=TZkP8kgJSYKx9in_kfce3w2jrF38A60B61rJEimJrPc,119682
|
718
768
|
sglang/srt/models/deepseek_vl2.py,sha256=7X3gI4DE7guUtNJvMLf06jO8MUHKa2Aan8evZg5hsXc,13061
|
719
|
-
sglang/srt/models/
|
769
|
+
sglang/srt/models/dots_vlm.py,sha256=0tbeQHbJryUMVqEnWelawDabzhcdwSj3Bb9-nj4YOKs,7242
|
770
|
+
sglang/srt/models/dots_vlm_vit.py,sha256=K6QzcHx38XAq9fmNRJ-iApScZ9FoV0lkn3JYkRsxplk,12044
|
771
|
+
sglang/srt/models/ernie4.py,sha256=3z14KFdYLR8J-zsm9oO1uBUeLlWrlkHoFKEYvKKJLKM,16079
|
720
772
|
sglang/srt/models/ernie4_eagle.py,sha256=E7f-ygCcY8pIoyTMKFyVC2uRcG59-_RaQTO4gd5_uWI,7223
|
721
773
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
722
774
|
sglang/srt/models/gemma.py,sha256=2atKwFN5wCsJCmBRmURX9vaCcFjxlFirL7xsnG5KPlI,14180
|
@@ -726,15 +778,15 @@ sglang/srt/models/gemma3_causal.py,sha256=0FdI0wVoJ4ZakBl8ShO29D1uEMO0T8CRjdsfiH
|
|
726
778
|
sglang/srt/models/gemma3_mm.py,sha256=sRvdAOiStlDhC_-sSH226d0awx4ZQJG7Wtdf7PE6ygw,17189
|
727
779
|
sglang/srt/models/gemma3n_audio.py,sha256=isgKfjA5UieYawxU6medL2ssXlzYPqAbagDBnLcemC0,36405
|
728
780
|
sglang/srt/models/gemma3n_causal.py,sha256=kBDlpSWAg6ZDmUPe08Q7sj5CbdVD_0h07zwJw8sKu7I,36335
|
729
|
-
sglang/srt/models/gemma3n_mm.py,sha256=
|
781
|
+
sglang/srt/models/gemma3n_mm.py,sha256=Kp2Wu-LFoDNU-OHD8Y0tSGGmu9cjkFr-2cHe9wxJ0Kg,20365
|
730
782
|
sglang/srt/models/glm4.py,sha256=dijzVTTgg8zyJ3gga95MKY0WwqwnuAaf-VIV93OFAmc,11433
|
731
|
-
sglang/srt/models/glm4_moe.py,sha256=
|
783
|
+
sglang/srt/models/glm4_moe.py,sha256=RXxrbu2wMENr25x8KMSQZ5z9_Q4-f-6DOLVOZchyEbk,42006
|
732
784
|
sglang/srt/models/glm4_moe_nextn.py,sha256=EuDWOBSd0oFfdvloePlpzAL81M_L7oz0BiWm74RQioc,5943
|
733
|
-
sglang/srt/models/glm4v.py,sha256=
|
734
|
-
sglang/srt/models/glm4v_moe.py,sha256=
|
785
|
+
sglang/srt/models/glm4v.py,sha256=_yt82CUUasko--6ew7d2hrXtqoxa0nE_4ikPdBL7thI,23755
|
786
|
+
sglang/srt/models/glm4v_moe.py,sha256=U6FgVrsHeY-fnkGaS_MlwHpnTvYUIdVlidEHeOLI4aE,17390
|
735
787
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
736
788
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
737
|
-
sglang/srt/models/gpt_oss.py,sha256=
|
789
|
+
sglang/srt/models/gpt_oss.py,sha256=rOjCpqbFsVdD5fVZOkhvm4ZmRIpmqgyjKvLPmPOL5LY,44481
|
738
790
|
sglang/srt/models/granite.py,sha256=8q92shxVPAp_cJDohJATffSGd7Z0Oi-vF5jpY6DlK4s,19840
|
739
791
|
sglang/srt/models/granitemoe.py,sha256=j1rgZ62CbBioECjUblDCw_NneDQgY_QJODsI0fqXVO8,13779
|
740
792
|
sglang/srt/models/grok.py,sha256=8KCR13LtdnhswJrIwgb0sdFW0OxCA8GQ0fbN8gb856E,40518
|
@@ -747,15 +799,15 @@ sglang/srt/models/internvl.py,sha256=iQm2wDtkcyjPYoV9oY_jQ3_7WvhP315eP_vZEiQX3uw
|
|
747
799
|
sglang/srt/models/kimi_vl.py,sha256=XulRiufQzOSWZe8-bUl2OEdznvsVU9OBsEYipaX3YkM,12877
|
748
800
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
749
801
|
sglang/srt/models/llama.py,sha256=tdyUon6icwzqo4XTAkFxVA2f82g80AGr9ZezK1uXmkM,28126
|
750
|
-
sglang/srt/models/llama4.py,sha256=
|
802
|
+
sglang/srt/models/llama4.py,sha256=i4-Vo5FVE9zf_6Y80dyft5VjPOQ-a-xWYfEV8s-ltKQ,19872
|
751
803
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
752
804
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
753
|
-
sglang/srt/models/llama_eagle3.py,sha256=
|
805
|
+
sglang/srt/models/llama_eagle3.py,sha256=lutyS4UaPg5QussPu08En3iO5e1lhsSm4dBXTm4R_XI,9201
|
754
806
|
sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OWYfirZnA,3254
|
755
807
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
756
808
|
sglang/srt/models/llava.py,sha256=xzYip_BAwpzSIdZre43LZiyTpFISa0ZCLdO6LUSbaCg,37702
|
757
809
|
sglang/srt/models/llavavid.py,sha256=-CSk0RJ2MQeb81sh-RISeVJFaI-XWY6nR6_I594MkME,12818
|
758
|
-
sglang/srt/models/longcat_flash.py,sha256=
|
810
|
+
sglang/srt/models/longcat_flash.py,sha256=lC_oa4n4bTmIV1TLJ9fn3r_Nzn7_5H0orQ8fQKpZ7rM,41055
|
759
811
|
sglang/srt/models/longcat_flash_nextn.py,sha256=oVy776-AE5z43C472oqHlcl9NfzDDEaQgGB1msZNdgc,29644
|
760
812
|
sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
761
813
|
sglang/srt/models/mimo_mtp.py,sha256=jSmqJAXu7G3OO7jW1oa2suI4H_Yl7u5ZT7w4lHFbHhg,7292
|
@@ -767,11 +819,12 @@ sglang/srt/models/mistral.py,sha256=ni7PppA_5X4ivTnIps3yoEaMEL-G6Gaf9b5hGC1vU5Q,
|
|
767
819
|
sglang/srt/models/mixtral.py,sha256=ohZVFJ75QWuE2kBKD7Sd4fcx9YbbjA7JxnYAsOIfORU,17166
|
768
820
|
sglang/srt/models/mixtral_quant.py,sha256=UUIq7lpUonD9IoGePyl59oJYEcVwT9wUXvtVp5tjQ9Y,15406
|
769
821
|
sglang/srt/models/mllama.py,sha256=OdX7brhyfGiMFPulxF77QOUi-Kcscg3Qo4ipyxzs9yA,39670
|
770
|
-
sglang/srt/models/mllama4.py,sha256=
|
822
|
+
sglang/srt/models/mllama4.py,sha256=k4L6haSwh2L-ql6BRkvthAMJ_aZXkRBn9WwFrBExYaQ,35746
|
771
823
|
sglang/srt/models/nemotron_nas.py,sha256=CoSAKqlbej4Xe30uY4w76iASBqeuJf8-imisDK00zEU,15964
|
772
824
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
773
825
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
774
826
|
sglang/srt/models/olmoe.py,sha256=zryYUQEhEdhd6xcR_HyLV7gHCcKt-HWHeEeIUqmhmcc,16100
|
827
|
+
sglang/srt/models/opt.py,sha256=1fdsQU7yXSN9HEWb0ZVdiAF8wLzAunW4XomIrlHyu2o,23476
|
775
828
|
sglang/srt/models/persimmon.py,sha256=86Duo3HiZqDj9O2UzWbJgUEhQOXzGBUdhUofQhcs1VE,11244
|
776
829
|
sglang/srt/models/phi.py,sha256=n6A1d47MvnR1lmSsZ3TuzXk5kT1Lntj_YQ5uNvR0s5o,10287
|
777
830
|
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
@@ -781,22 +834,24 @@ sglang/srt/models/phi4mm_utils.py,sha256=bW3un4x3SHDvSkAOHQEFO286FGdOPeKhBpJCOmN
|
|
781
834
|
sglang/srt/models/phimoe.py,sha256=EGaKFi02MZP20qFrILA4o2SJ0wb1HoJagFTSqVUbJcQ,19223
|
782
835
|
sglang/srt/models/pixtral.py,sha256=ZkZrV0mEfmbBdgRko2AvsMFZbAVskgp_5a5p1xCSRN0,16835
|
783
836
|
sglang/srt/models/qwen.py,sha256=j0OU3JjznWi_TbayI09yYGM-Obov6mQzJO82Hs0qBGw,11868
|
784
|
-
sglang/srt/models/qwen2.py,sha256=
|
785
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
837
|
+
sglang/srt/models/qwen2.py,sha256=xptcdyvkQKYj0N67h6391hGAzfTxQN1hVhdBfK56FEA,23813
|
838
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=zluJM8KyyjQBV0KfhgdsCcPSKD1QTokhZS7a8JK5w0g,25008
|
786
839
|
sglang/srt/models/qwen2_audio.py,sha256=SOOsspU7J6eM-iSkms5op0nWhoxJd6QxmwXU2aQBEEQ,7776
|
787
840
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
788
841
|
sglang/srt/models/qwen2_eagle.py,sha256=6spFg6JYQGeUXLv2Q5eMkVzZvnqGyvW6SdVBtFMxlTM,4806
|
789
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
842
|
+
sglang/srt/models/qwen2_moe.py,sha256=sbD9hFrP6ebsvt81rI_O2tva05KnQp-0TLiAUThza1k,28439
|
790
843
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
791
844
|
sglang/srt/models/qwen2_vl.py,sha256=ZRAL32Ymt4ZCBqB0JorXAm4ZBrECZ9EbaXKaTSikkQM,21366
|
792
845
|
sglang/srt/models/qwen3.py,sha256=cfp7rL20_E4PyPii85gnXsfsje9b_WK3br-sbYikd0E,19324
|
793
846
|
sglang/srt/models/qwen3_classification.py,sha256=bdjAylXJCjXKjAho74nmtIMpEG0Af98N-aZQ-pKKMY0,3262
|
794
|
-
sglang/srt/models/qwen3_moe.py,sha256
|
847
|
+
sglang/srt/models/qwen3_moe.py,sha256=9w0pznGrSYhBUZuPaYLQs8x6oaaf75Ir95g9UffxMf4,33210
|
848
|
+
sglang/srt/models/qwen3_next.py,sha256=f6zAvdeIf-wi1DXS7LLx3O7MZrUdJ14-yLnUDri-w6g,36508
|
849
|
+
sglang/srt/models/qwen3_next_mtp.py,sha256=F-NnFGer8KxijNKIZoKICDfp6iFwct-XV0-q0KxAApg,4465
|
795
850
|
sglang/srt/models/registry.py,sha256=kKQ5ruD6_c3JxWsykOoxt-hroSlslv-Niz0nYvHrhGg,3779
|
796
851
|
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
797
852
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
798
853
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
799
|
-
sglang/srt/models/step3_vl.py,sha256=
|
854
|
+
sglang/srt/models/step3_vl.py,sha256=4j7drPJT2h-QwFH7tK7zR96xnuGvrxNbestuZsflCxg,35666
|
800
855
|
sglang/srt/models/torch_native_llama.py,sha256=qavMy0wjaX18pM7UJscjoOpSKWgDT_INlnImU6OJ4Lw,18327
|
801
856
|
sglang/srt/models/transformers.py,sha256=laA2h39MPeiAWKv4DEg0ydre-1pyXWFSRga-nwy1HUk,10244
|
802
857
|
sglang/srt/models/vila.py,sha256=3NiRHWOqXnCRjXmswAldsNtiE5zRILbScEsbhUzLZF4,9846
|
@@ -807,10 +862,11 @@ sglang/srt/multimodal/mm_utils.py,sha256=6bV1_a7Iet9W0y3qdd0E-hFM78zalIzNZCYbLzJ
|
|
807
862
|
sglang/srt/multimodal/processors/base_processor.py,sha256=G25SF9bIyoQ13v7Qsb2ZDWTBq-BJ8Sa9okGZPPsS2TM,24518
|
808
863
|
sglang/srt/multimodal/processors/clip.py,sha256=5nXZuQYbyf-5mlqPwjhQrlWqxvswImWZQXivChsiHfQ,1057
|
809
864
|
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=Pymag9f0U5L_bBOTFs2q94BbuPJ-VwqSixs3meO0nsM,2569
|
865
|
+
sglang/srt/multimodal/processors/dots_vlm.py,sha256=r_vd0yZ10GJ0ib8_xNl7edJHxAa5-c7q8XjwpiEqwdY,3457
|
810
866
|
sglang/srt/multimodal/processors/gemma3.py,sha256=7aD6cR60iSC_MqjzdCDMAgtrb_cmy9YJyqLgVRClBT8,1986
|
811
867
|
sglang/srt/multimodal/processors/gemma3n.py,sha256=mtmvBasOMxb3Y2NLZR02nMYX30RLUXhDYJ5uVOElr10,2776
|
812
|
-
sglang/srt/multimodal/processors/glm4v.py,sha256=
|
813
|
-
sglang/srt/multimodal/processors/internvl.py,sha256=
|
868
|
+
sglang/srt/multimodal/processors/glm4v.py,sha256=SQXatu6t-YgE8wNSavBRliN7J4DqiP57lmA47-zRlYQ,4953
|
869
|
+
sglang/srt/multimodal/processors/internvl.py,sha256=1fYa9MdbxJnKc9vfUiyqxsiO0H_aaW3uUI1-0LoXKHo,9976
|
814
870
|
sglang/srt/multimodal/processors/janus_pro.py,sha256=_4ltWmdtFjbh1VCMRbcgxW61eWIABIzHG-YgwHWaYq8,1471
|
815
871
|
sglang/srt/multimodal/processors/kimi_vl.py,sha256=5i8KmGxnnDtQc7XqUBNyanAfGxhxj8iRFBFONHmpiFg,1565
|
816
872
|
sglang/srt/multimodal/processors/llava.py,sha256=-YtDc_7TsMWmwKkD4KJZW2Y0jPFlZtbQ38K_N24hk0w,8231
|
@@ -820,7 +876,7 @@ sglang/srt/multimodal/processors/mllama4.py,sha256=1YGETKSzMZIa7BOwq3T9cbsYjUcW5
|
|
820
876
|
sglang/srt/multimodal/processors/phi4mm.py,sha256=8GaUVpGucV4UKoa0XkxN0gDpMZax6UyCiRBX_QaJK78,3857
|
821
877
|
sglang/srt/multimodal/processors/pixtral.py,sha256=Lx5Z-9NkovLDTHlRBznHxGn4r2XhDz8am2XpOskOVQY,3203
|
822
878
|
sglang/srt/multimodal/processors/qwen_audio.py,sha256=xkIFrHepF8Ok6MB-1OwVz1BmzPmEPgUe8lIb0azO2Bc,2411
|
823
|
-
sglang/srt/multimodal/processors/qwen_vl.py,sha256=
|
879
|
+
sglang/srt/multimodal/processors/qwen_vl.py,sha256=fZFWI07kF-2kde71Rmtodu75FKj8JFFfwYuJaFNWEVw,10726
|
824
880
|
sglang/srt/multimodal/processors/step3_vl.py,sha256=9OI6UW9ybGbAnYN_S-5jh7TN8BGM_bQkvh1AHBJKzAQ,18350
|
825
881
|
sglang/srt/multimodal/processors/vila.py,sha256=vWgV1lTdjiFiTR8w-7fC66-L_tpOOD59c-c9NljGelE,2192
|
826
882
|
sglang/srt/parser/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
@@ -829,7 +885,7 @@ sglang/srt/parser/harmony_parser.py,sha256=YweG4azWm5jmzYGaAHEXSaORpgWctPpSGQk_j
|
|
829
885
|
sglang/srt/parser/jinja_template_utils.py,sha256=XCuqi6iHQrtziUvhy22ePdh8WcS42O9sKxuXpM_bMXc,7836
|
830
886
|
sglang/srt/parser/reasoning_parser.py,sha256=3P5viZ4oCsz695rZULWnRKSYBJxouHjihdpZMBuY9yc,11159
|
831
887
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
832
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
888
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=0hPeAOJeJZdVets_Kseh2RZUtS4n96pMa4kJr227Ltk,14852
|
833
889
|
sglang/srt/sampling/sampling_params.py,sha256=HbVcCeSXgPW19MRB-v0FTG1D-zHDAY6-toxyndSl-zI,6462
|
834
890
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
835
891
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
@@ -837,20 +893,22 @@ sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4T
|
|
837
893
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=Romk41ahToaVlNMnnd1Enko7_kRA4KdMGO94qnEbDHA,6061
|
838
894
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
839
895
|
sglang/srt/speculative/build_eagle_tree.py,sha256=O9LJNaBflgJdWT94D-rGH1gJFJ18nst2oOD8HnA2mZ4,12859
|
840
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=
|
841
|
-
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=
|
842
|
-
sglang/srt/speculative/eagle_utils.py,sha256=
|
843
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
844
|
-
sglang/srt/speculative/spec_info.py,sha256=
|
896
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=4U4ubjqihqRAio5YzEksu56NXDRDQFVsriQ9sDWTexc,14167
|
897
|
+
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=FgKuBfDYYF5DnNTstRJ4t6lgrI-YuLTaTvCs7HH22qA,15818
|
898
|
+
sglang/srt/speculative/eagle_utils.py,sha256=xYzAgwfcSBNfgdj-Wd8_y6ds78NRf3TgMA44qS5M_WM,47747
|
899
|
+
sglang/srt/speculative/eagle_worker.py,sha256=MTEGRY5z405jS2CTCEC_wPlWRnnsYY6IkIYqSAhZJH0,45476
|
900
|
+
sglang/srt/speculative/spec_info.py,sha256=f0d2-Zm8egnGBxqW4-OFOi9eaYk4KL4LZnc-e_c7dS4,877
|
901
|
+
sglang/srt/speculative/standalone_worker.py,sha256=jcM_-7DMtRUMC9R0YeD6815kaWuftkFe8LIo7ThLVCc,4069
|
845
902
|
sglang/srt/tokenizer/tiktoken_tokenizer.py,sha256=KJwr6Xlc7AdHegMTnAVKJlPpW59Z7AE27GTzFL78GwI,6222
|
903
|
+
sglang/srt/tracing/trace.py,sha256=QKeo0Nzj_AAIcCMZ6ijQxlQt1DZDiAhdLNAKIrbTV-8,15708
|
846
904
|
sglang/srt/weight_sync/tensor_bucket.py,sha256=vp_LRrhULNnxiw9Tf56FcEckgUg07lifgv1lasG6y7o,3695
|
847
|
-
sglang/srt/weight_sync/utils.py,sha256=
|
905
|
+
sglang/srt/weight_sync/utils.py,sha256=WoZH_5qJTey-aV-qPgOgYoaGeAwrOy7Z8pQZREpgUaA,4149
|
848
906
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
849
907
|
sglang/test/doc_patch.py,sha256=P9PYjBIVlZHvP9M34qS-8m1scmDP27ciNJNvZOdrUKE,1614
|
850
908
|
sglang/test/few_shot_gsm8k.py,sha256=zalplyHOYCnIwAnSQg-xlZl-Q-wGuMfjLdl9EJnUN7U,4333
|
851
909
|
sglang/test/few_shot_gsm8k_engine.py,sha256=h88s3HzEStA1zjQkR-AgIEOQMwJMSnPHkX_wGBWXUYw,3907
|
852
910
|
sglang/test/run_eval.py,sha256=VnbcmUhceDUU3-nXlZ6uQMM3MEvnZh1gzP3LXxYkuxc,4251
|
853
|
-
sglang/test/runners.py,sha256=
|
911
|
+
sglang/test/runners.py,sha256=HenubP5mlRQ2i3G8pS9q4gdzYGC0cVSIbaAjKmmkPac,34099
|
854
912
|
sglang/test/send_one.py,sha256=XNZdfZs21tXDBwrDj2pq46WQd5smiKoYETY8U09c1Z8,5079
|
855
913
|
sglang/test/simple_eval_common.py,sha256=B60Yi3ox2Yubsq8M3BbApQTfmLhwQoL4ciS2ac12SM4,12702
|
856
914
|
sglang/test/simple_eval_gpqa.py,sha256=M6hpPs8l2Z4wUiyE7rCU1zyKoImXB4Z395Hgz43uvvQ,3293
|
@@ -863,23 +921,24 @@ sglang/test/test_block_fp8.py,sha256=mOM-eX9LisotPlMLSCvH4XwWMbvNpVOBtt7euXuVTDw
|
|
863
921
|
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7Xx0MjOoOBYL8J7ETvOVA,8180
|
864
922
|
sglang/test/test_block_fp8_ep.py,sha256=n4X6ZKwuUUbV5Ofjg64ptlaFGI1LbRXDfFiJW1ELHgY,10546
|
865
923
|
sglang/test/test_custom_ops.py,sha256=PenQ8zM1wj5xwiVEPVzD37pO-x90aOfFMpCRZenaKsY,5709
|
866
|
-
sglang/test/test_cutlass_moe.py,sha256=
|
924
|
+
sglang/test/test_cutlass_moe.py,sha256=WHCruIMzxzRzxQEeFEUtk0e0IefjiO0Kjfgnx42r0UI,10069
|
867
925
|
sglang/test/test_cutlass_w4a8_moe.py,sha256=Ku9VCXEMJ3BwXtvb1A3FzY-zek-S-A4thWyX6m-1v-A,9219
|
868
926
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
927
|
+
sglang/test/test_disaggregation_utils.py,sha256=S9GbriBYqbxpG-GZXs6wafeo4IFAFL7xAUHJSZ6RDpE,1962
|
869
928
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
870
|
-
sglang/test/test_fp4_moe.py,sha256=
|
929
|
+
sglang/test/test_fp4_moe.py,sha256=wvHbGMH1UBr_XVWYgX57Y2bLy9h2DPQH10_Hmf2q6iw,22436
|
871
930
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
872
931
|
sglang/test/test_marlin_moe.py,sha256=TOuYlVMx2Lv_IN3AMWsg5aGaxQF472E1B9ev_vvfU2Q,7971
|
873
932
|
sglang/test/test_marlin_utils.py,sha256=kC7IzN364mJT9xw0nKUP1V1OK1hkw6fQTBvD4nRaOz4,5151
|
874
933
|
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
875
|
-
sglang/test/test_utils.py,sha256=
|
934
|
+
sglang/test/test_utils.py,sha256=QjsWnlC--xO2wVuRge5y4INsgYaMRZxkcIRpSZS4_DU,42455
|
876
935
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
877
936
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
878
937
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
879
938
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
880
|
-
sglang/test/attention/test_trtllm_mla_backend.py,sha256=
|
881
|
-
sglang-0.5.
|
882
|
-
sglang-0.5.
|
883
|
-
sglang-0.5.
|
884
|
-
sglang-0.5.
|
885
|
-
sglang-0.5.
|
939
|
+
sglang/test/attention/test_trtllm_mla_backend.py,sha256=wp2_LSTwQ_vIdNPUCbEz7PA4doDU8sTWs6s6XVI0YnI,48874
|
940
|
+
sglang-0.5.3rc0.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
941
|
+
sglang-0.5.3rc0.dist-info/METADATA,sha256=CVn-KgB7MsFTUz4NVra4mQQRyPOYxtxiXSTPjzl8Cyw,24232
|
942
|
+
sglang-0.5.3rc0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
943
|
+
sglang-0.5.3rc0.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
944
|
+
sglang-0.5.3rc0.dist-info/RECORD,,
|