sglang 0.5.1.post2__py3-none-any.whl → 0.5.2__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 +3 -0
- sglang/bench_one_batch_server.py +89 -54
- sglang/bench_serving.py +437 -40
- sglang/lang/interpreter.py +1 -1
- sglang/profiler.py +0 -1
- sglang/srt/configs/__init__.py +4 -0
- sglang/srt/configs/internvl.py +6 -0
- sglang/srt/configs/longcat_flash.py +104 -0
- sglang/srt/configs/model_config.py +37 -7
- sglang/srt/configs/qwen3_next.py +326 -0
- sglang/srt/connector/__init__.py +1 -1
- sglang/srt/connector/base_connector.py +1 -2
- sglang/srt/connector/redis.py +2 -2
- sglang/srt/connector/serde/__init__.py +1 -1
- sglang/srt/connector/serde/safe_serde.py +4 -3
- 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/ascend/conn.py +75 -0
- sglang/srt/disaggregation/base/conn.py +1 -1
- sglang/srt/disaggregation/common/conn.py +15 -12
- sglang/srt/disaggregation/decode.py +6 -4
- sglang/srt/disaggregation/fake/conn.py +1 -1
- sglang/srt/disaggregation/mini_lb.py +6 -420
- sglang/srt/disaggregation/mooncake/conn.py +18 -10
- sglang/srt/disaggregation/nixl/conn.py +180 -16
- sglang/srt/disaggregation/prefill.py +6 -4
- sglang/srt/disaggregation/utils.py +5 -50
- sglang/srt/distributed/parallel_state.py +94 -58
- sglang/srt/entrypoints/engine.py +34 -14
- sglang/srt/entrypoints/http_server.py +172 -47
- sglang/srt/entrypoints/openai/protocol.py +90 -27
- sglang/srt/entrypoints/openai/serving_base.py +6 -2
- sglang/srt/entrypoints/openai/serving_chat.py +82 -26
- sglang/srt/entrypoints/openai/serving_completions.py +25 -4
- sglang/srt/entrypoints/openai/serving_embedding.py +8 -4
- sglang/srt/entrypoints/openai/serving_responses.py +7 -4
- sglang/srt/eplb/eplb_manager.py +28 -4
- sglang/srt/eplb/expert_distribution.py +55 -15
- sglang/srt/eplb/expert_location.py +8 -3
- sglang/srt/eplb/expert_location_updater.py +1 -1
- sglang/srt/function_call/deepseekv31_detector.py +222 -0
- sglang/srt/function_call/ebnf_composer.py +11 -9
- sglang/srt/function_call/function_call_parser.py +2 -0
- sglang/srt/function_call/glm4_moe_detector.py +1 -1
- sglang/srt/function_call/gpt_oss_detector.py +144 -256
- sglang/srt/function_call/qwen3_coder_detector.py +1 -1
- sglang/srt/hf_transformers_utils.py +28 -7
- sglang/srt/layers/activation.py +44 -9
- sglang/srt/layers/attention/aiter_backend.py +93 -68
- sglang/srt/layers/attention/ascend_backend.py +381 -136
- 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/flashattention_backend.py +241 -7
- sglang/srt/layers/attention/flashinfer_backend.py +11 -6
- sglang/srt/layers/attention/flashinfer_mla_backend.py +21 -14
- sglang/srt/layers/attention/hybrid_attn_backend.py +47 -8
- sglang/srt/layers/attention/hybrid_linear_attn_backend.py +584 -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/trtllm_mla_backend.py +126 -36
- 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/communicator.py +45 -8
- sglang/srt/layers/layernorm.py +54 -12
- sglang/srt/layers/logits_processor.py +10 -3
- sglang/srt/layers/moe/__init__.py +2 -1
- sglang/srt/layers/moe/cutlass_moe.py +0 -8
- sglang/srt/layers/moe/cutlass_w4a8_moe.py +4 -12
- sglang/srt/layers/moe/ep_moe/kernels.py +74 -0
- sglang/srt/layers/moe/ep_moe/layer.py +111 -56
- sglang/srt/layers/moe/fused_moe_native.py +5 -3
- sglang/srt/layers/moe/fused_moe_triton/__init__.py +5 -3
- 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 +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +146 -0
- 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 → E=257,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json } +29 -29
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=64,device_name=NVIDIA_A100-SXM4-80GB.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=256,device_name=NVIDIA_H20-3e.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/fused_moe.py +9 -1049
- sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py +212 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py +799 -0
- sglang/srt/layers/moe/fused_moe_triton/layer.py +56 -45
- sglang/srt/layers/moe/fused_moe_triton/moe_align_block_size.py +87 -0
- 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 +41 -38
- sglang/srt/layers/moe/token_dispatcher/standard.py +44 -2
- sglang/srt/layers/moe/topk.py +43 -12
- sglang/srt/layers/moe/utils.py +6 -5
- 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/compile_utils.py +141 -235
- sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py +5 -10
- sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py +31 -22
- sglang/srt/layers/quantization/fp8.py +78 -48
- sglang/srt/layers/quantization/fp8_kernel.py +2 -2
- sglang/srt/layers/quantization/fp8_utils.py +45 -31
- sglang/srt/layers/quantization/gptq.py +25 -17
- sglang/srt/layers/quantization/modelopt_quant.py +107 -40
- sglang/srt/layers/quantization/moe_wna16.py +21 -18
- sglang/srt/layers/quantization/mxfp4.py +93 -68
- sglang/srt/layers/quantization/mxfp4_tensor.py +3 -1
- sglang/srt/layers/quantization/quark/quark_moe.py +32 -27
- sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py +49 -30
- sglang/srt/layers/quantization/quark/utils.py +97 -0
- sglang/srt/layers/quantization/rocm_mxfp4_utils.py +13 -0
- sglang/srt/layers/quantization/unquant.py +135 -47
- sglang/srt/layers/quantization/utils.py +13 -0
- sglang/srt/layers/quantization/w4afp8.py +60 -42
- sglang/srt/layers/quantization/w8a8_fp8.py +35 -20
- sglang/srt/layers/quantization/w8a8_int8.py +83 -41
- sglang/srt/layers/rocm_linear_utils.py +44 -0
- sglang/srt/layers/rotary_embedding.py +28 -19
- sglang/srt/layers/sampler.py +29 -5
- sglang/srt/layers/utils.py +0 -14
- 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/cache_controller.py +396 -365
- sglang/srt/managers/data_parallel_controller.py +30 -15
- sglang/srt/managers/detokenizer_manager.py +18 -2
- sglang/srt/managers/disagg_service.py +46 -0
- sglang/srt/managers/io_struct.py +190 -11
- sglang/srt/managers/mm_utils.py +6 -1
- sglang/srt/managers/multi_tokenizer_mixin.py +579 -0
- sglang/srt/managers/schedule_batch.py +27 -44
- sglang/srt/managers/schedule_policy.py +4 -3
- sglang/srt/managers/scheduler.py +148 -122
- sglang/srt/managers/scheduler_metrics_mixin.py +114 -8
- sglang/srt/managers/scheduler_output_processor_mixin.py +29 -19
- sglang/srt/managers/scheduler_profiler_mixin.py +1 -1
- sglang/srt/managers/scheduler_update_weights_mixin.py +8 -1
- sglang/srt/managers/template_manager.py +3 -3
- sglang/srt/managers/tokenizer_communicator_mixin.py +491 -0
- sglang/srt/managers/tokenizer_manager.py +77 -480
- sglang/srt/managers/tp_worker.py +16 -4
- sglang/srt/managers/tp_worker_overlap_thread.py +8 -10
- sglang/srt/mem_cache/allocator.py +1 -1
- sglang/srt/mem_cache/chunk_cache.py +1 -1
- sglang/srt/mem_cache/hicache_storage.py +53 -40
- sglang/srt/mem_cache/hiradix_cache.py +196 -104
- sglang/srt/mem_cache/lora_radix_cache.py +1 -1
- sglang/srt/mem_cache/memory_pool.py +395 -53
- sglang/srt/mem_cache/memory_pool_host.py +27 -19
- sglang/srt/mem_cache/radix_cache.py +6 -6
- sglang/srt/mem_cache/radix_cache_cpp.py +1 -1
- 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/mini_3fs_metadata_server.py +61 -34
- sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py +152 -23
- 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 +154 -95
- sglang/srt/mem_cache/storage/mooncake_store/test_mooncake_store.py +161 -0
- sglang/srt/mem_cache/swa_radix_cache.py +1 -3
- sglang/srt/metrics/collector.py +484 -63
- sglang/srt/metrics/startup_func_log_and_timer.py +150 -0
- sglang/srt/metrics/utils.py +48 -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 +72 -18
- sglang/srt/model_executor/model_runner.py +190 -32
- sglang/srt/model_loader/__init__.py +9 -3
- sglang/srt/model_loader/loader.py +33 -28
- sglang/srt/model_loader/utils.py +12 -0
- sglang/srt/model_loader/weight_utils.py +2 -1
- sglang/srt/models/deepseek_v2.py +323 -53
- sglang/srt/models/gemma3n_mm.py +1 -1
- sglang/srt/models/glm4_moe.py +10 -1
- sglang/srt/models/glm4v.py +4 -2
- sglang/srt/models/gpt_oss.py +7 -19
- sglang/srt/models/internvl.py +28 -0
- sglang/srt/models/llama4.py +9 -0
- sglang/srt/models/llama_eagle3.py +17 -0
- sglang/srt/models/longcat_flash.py +1026 -0
- sglang/srt/models/longcat_flash_nextn.py +699 -0
- sglang/srt/models/minicpmv.py +165 -3
- sglang/srt/models/mllama4.py +25 -0
- sglang/srt/models/opt.py +637 -0
- sglang/srt/models/qwen2.py +33 -3
- sglang/srt/models/qwen2_5_vl.py +91 -42
- sglang/srt/models/qwen2_moe.py +79 -14
- sglang/srt/models/qwen3.py +8 -2
- sglang/srt/models/qwen3_moe.py +39 -8
- sglang/srt/models/qwen3_next.py +1039 -0
- sglang/srt/models/qwen3_next_mtp.py +109 -0
- sglang/srt/models/torch_native_llama.py +1 -1
- sglang/srt/models/transformers.py +1 -1
- sglang/srt/multimodal/processors/base_processor.py +4 -2
- sglang/srt/multimodal/processors/glm4v.py +9 -9
- sglang/srt/multimodal/processors/internvl.py +141 -129
- sglang/srt/{conversation.py → parser/conversation.py} +38 -5
- sglang/srt/parser/harmony_parser.py +588 -0
- sglang/srt/parser/reasoning_parser.py +309 -0
- sglang/srt/sampling/penaltylib/orchestrator.py +14 -2
- sglang/srt/sampling/sampling_batch_info.py +18 -15
- sglang/srt/server_args.py +307 -80
- 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_worker.py +216 -120
- sglang/srt/speculative/spec_info.py +5 -0
- sglang/srt/speculative/standalone_worker.py +109 -0
- sglang/srt/tokenizer/tiktoken_tokenizer.py +6 -1
- sglang/srt/utils.py +96 -7
- sglang/srt/weight_sync/utils.py +1 -1
- sglang/test/attention/test_trtllm_mla_backend.py +181 -8
- sglang/test/few_shot_gsm8k.py +1 -0
- sglang/test/runners.py +4 -0
- sglang/test/test_cutlass_moe.py +24 -6
- sglang/test/test_cutlass_w4a8_moe.py +24 -9
- sglang/test/test_disaggregation_utils.py +66 -0
- sglang/test/test_utils.py +25 -1
- sglang/utils.py +5 -0
- sglang/version.py +1 -1
- {sglang-0.5.1.post2.dist-info → sglang-0.5.2.dist-info}/METADATA +13 -10
- {sglang-0.5.1.post2.dist-info → sglang-0.5.2.dist-info}/RECORD +253 -201
- sglang/srt/disaggregation/launch_lb.py +0 -131
- sglang/srt/mem_cache/storage/mooncake_store/unit_test.py +0 -40
- sglang/srt/reasoning_parser.py +0 -553
- /sglang/srt/{model_parallel.py → layers/model_parallel.py} +0 -0
- /sglang/srt/{code_completion_parser.py → parser/code_completion_parser.py} +0 -0
- /sglang/srt/{jinja_template_utils.py → parser/jinja_template_utils.py} +0 -0
- {sglang-0.5.1.post2.dist-info → sglang-0.5.2.dist-info}/WHEEL +0 -0
- {sglang-0.5.1.post2.dist-info → sglang-0.5.2.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.5.1.post2.dist-info → sglang-0.5.2.dist-info}/top_level.txt +0 -0
@@ -1,22 +1,22 @@
|
|
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=
|
3
|
+
sglang/bench_one_batch.py,sha256=ITGCBFPksSyoXPEgAqZruGY2ZUPyOoc111jf1nil0go,23137
|
4
|
+
sglang/bench_one_batch_server.py,sha256=WQeZCpqdJIUIel950_uzgH2d2LYUXXnIkwcspGI37xs,14967
|
5
|
+
sglang/bench_serving.py,sha256=d6E3h9Fy6byXubEabje0-MRXc2lcrUQLIwanHxZk_S4,87491
|
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
|
-
sglang/profiler.py,sha256=
|
11
|
-
sglang/utils.py,sha256=
|
12
|
-
sglang/version.py,sha256=
|
10
|
+
sglang/profiler.py,sha256=JCpZzlDhahoiPlPi5IG3n7GFrQHxfHEB6ELie3Ck55w,4397
|
11
|
+
sglang/utils.py,sha256=buvRAp_XbqhBvCpzvEUzqBiaD0iCTDX2ayT9vmIwyJI,16625
|
12
|
+
sglang/version.py,sha256=isJrmDBLRag7Zc2UK9ZovWGOv7ji1Oh-zJtJMNJFkXw,22
|
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
|
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=
|
19
|
+
sglang/lang/interpreter.py,sha256=F-wxyKDUnTygmJpSEYsrQermls2RyWJntOep9_P7V1I,34818
|
20
20
|
sglang/lang/ir.py,sha256=FnRJ-lndAsR4GR0ONJRPDtlYx8FvL9RIk44vSA16RBk,19656
|
21
21
|
sglang/lang/tracer.py,sha256=ljBo9VZ0zVaGwzNk32qw21acyo60N0UjIjqBbT5a1WI,8175
|
22
22
|
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
@@ -28,47 +28,44 @@ sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZ
|
|
28
28
|
sglang/srt/_custom_ops.py,sha256=9GPNUyqnybgvUnzdQ8n5_NgluHmQNw0Gptos0iLPfrY,5342
|
29
29
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
30
30
|
sglang/srt/bench_utils.py,sha256=zNTsTBUta27XxojgvR5p5X9M0v1MFzZ7dcX9TMq4NvQ,4348
|
31
|
-
sglang/srt/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
32
31
|
sglang/srt/constants.py,sha256=0i-tEwG2BSYNDy96MxnGHV5HnBELkYcnsVGsE-R18o0,93
|
33
|
-
sglang/srt/
|
34
|
-
sglang/srt/
|
35
|
-
sglang/srt/hf_transformers_utils.py,sha256=WgpIr56YuKG8Hmp_vrZBfePYWMzDPVhH8k0p4DLk5sA,14877
|
32
|
+
sglang/srt/custom_op.py,sha256=m5F7x3LHlnOuesmcNmJtIWsfHGFLBJ807vKc05Gu1D0,3312
|
33
|
+
sglang/srt/hf_transformers_utils.py,sha256=qu2p2d3Vo0r7CLorQAc6hgxEz04FbpBL152ImNtHynY,15744
|
36
34
|
sglang/srt/host_shared_memory.py,sha256=00TgVm3PNCl4rTPJZChG5uu4I5hd_Xf587r39tibmIg,2274
|
37
|
-
sglang/srt/jinja_template_utils.py,sha256=XCuqi6iHQrtziUvhy22ePdh8WcS42O9sKxuXpM_bMXc,7836
|
38
|
-
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
39
35
|
sglang/srt/offloader.py,sha256=iu6Q5lOzJvuQVmq_CEYWitu41sNF1wmavTvOxlyEGaU,18097
|
40
36
|
sglang/srt/operations.py,sha256=za_h1_kcR1Te6-i_r0i_zAeumbmIRhLK2pS31sukkrw,6089
|
41
37
|
sglang/srt/operations_strategy.py,sha256=-w6GI2VgSGvORy3pUWRAJo6244ykSW1ZBV1Dx0fZlHA,7138
|
42
38
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
43
39
|
sglang/srt/poll_based_barrier.py,sha256=9vjn32ROlSueEk7EuZjWKUrrL7XVR9KJsSVliGTYB_4,937
|
44
|
-
sglang/srt/
|
45
|
-
sglang/srt/server_args.py,sha256=5IjWQay7BuqKtdt9LzpFXb24jo1ncqW3tVZ-7ho3GoY,102200
|
40
|
+
sglang/srt/server_args.py,sha256=CTfhxjhnuQMYBIUUJQ-gRyiU28q84FYxa_FP9g_LMxQ,111212
|
46
41
|
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
47
42
|
sglang/srt/two_batch_overlap.py,sha256=UykF5nC2rja3Hvmu0D9glqKdVRIEhQGPV84Jm7veopQ,34150
|
48
|
-
sglang/srt/utils.py,sha256=
|
43
|
+
sglang/srt/utils.py,sha256=8kD6zbg_3QAOtu9nMTU0yNDq7kOmTpzMXgZRq2JMYYI,96148
|
49
44
|
sglang/srt/warmup.py,sha256=zldxhMlXpclRAJXmfBjJNUJd1eDizVdysibBvQyTVuA,1782
|
50
|
-
sglang/srt/configs/__init__.py,sha256=
|
45
|
+
sglang/srt/configs/__init__.py,sha256=OfmjgqRee06qYaEaW4hQ88-vK-UUtkLTmyWAOYTa5JU,914
|
51
46
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
52
47
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
53
48
|
sglang/srt/configs/deepseekvl2.py,sha256=sYMmoy5_LlDXht7MTi4QGYOaiE8iMGUO44bnuOu4i8I,23683
|
54
49
|
sglang/srt/configs/device_config.py,sha256=kdwFrk5myAURxdp4rSr8ANpBpSJfuBDoT-kuCyuscRs,442
|
55
50
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
56
|
-
sglang/srt/configs/internvl.py,sha256=
|
51
|
+
sglang/srt/configs/internvl.py,sha256=rIC-CBWJHy-Mjmk0_H3YcvVmZzeCRbXGo3dQMex-yeg,28141
|
57
52
|
sglang/srt/configs/janus_pro.py,sha256=yI2c_aWBIKiTcK6RZxK6hq8CIxyYRH_NN8uaSNKsrKI,19156
|
58
53
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
59
54
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
60
55
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
61
|
-
sglang/srt/configs/
|
56
|
+
sglang/srt/configs/longcat_flash.py,sha256=Qp25xJVLq2K72Z80cXhcJxtqhagAdiPySDoevuT0Sno,3589
|
57
|
+
sglang/srt/configs/model_config.py,sha256=aHJAtuDxPRDDG8NRuzCjURuyU6C7CPIsa-v1O4-Pmgg,32275
|
58
|
+
sglang/srt/configs/qwen3_next.py,sha256=MVMDzdwlxrdar_6p6n9HjaXAei_giFfXlQNJAWpSLQ4,15794
|
62
59
|
sglang/srt/configs/step3_vl.py,sha256=_Otgnym57DVgB_kZ__8c1_Ys5gSalA_K0ZuVjcG51T0,4845
|
63
60
|
sglang/srt/configs/update_config.py,sha256=GEf-XhL8JPrbX9-Hz8V7S3M6YTg76DVdIhc_4YdMDtc,6291
|
64
61
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
65
|
-
sglang/srt/connector/__init__.py,sha256=
|
66
|
-
sglang/srt/connector/base_connector.py,sha256=
|
67
|
-
sglang/srt/connector/redis.py,sha256=
|
62
|
+
sglang/srt/connector/__init__.py,sha256=7sKpAYPdW9NC0A3sbUmDVgLuMf9b2jwifnVMs2Q7Ow4,1243
|
63
|
+
sglang/srt/connector/base_connector.py,sha256=LCKsTX_yWHclPrzNNB1fLwVCN8rIDKZaZhqHQ54B9MU,2774
|
64
|
+
sglang/srt/connector/redis.py,sha256=K3fJSm2rZsd0R_KkICV3jIWKtrwxXE1tYktWnovLbz4,2514
|
68
65
|
sglang/srt/connector/s3.py,sha256=hn5Ow9Y6ItS8RMJDwnTQe5QaiQ7HKMgiwggE9QnUewM,3743
|
69
66
|
sglang/srt/connector/utils.py,sha256=isTvxauz1_8no5MW6p8Bwj2H9mQkweaRO_RSwAPA7R8,983
|
70
|
-
sglang/srt/connector/serde/__init__.py,sha256=
|
71
|
-
sglang/srt/connector/serde/safe_serde.py,sha256=
|
67
|
+
sglang/srt/connector/serde/__init__.py,sha256=zuleyYN-jrDyiPiXjTbQKA27llb4H7HuDTZcBwrLk1U,707
|
68
|
+
sglang/srt/connector/serde/safe_serde.py,sha256=XSjb9mRv1HqeG6Jiw633EOQYlrcI23Q21UluYqPZaWA,760
|
72
69
|
sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOUIhF0ZA,1004
|
73
70
|
sglang/srt/constrained/base_grammar_backend.py,sha256=ATWX1LKp3GjUDVkauEaSc3MnS8Bt6hOiHUgeYDZtgNo,7059
|
74
71
|
sglang/srt/constrained/llguidance_backend.py,sha256=Au8G8x4EB39w7k9-GFLP2hOPETyeAPw53RRZYdLimpA,6191
|
@@ -78,35 +75,35 @@ sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuw
|
|
78
75
|
sglang/srt/constrained/xgrammar_backend.py,sha256=7mwm78Fx21psAseBrQlzVJuPg2YY5aw7GI6J6qLxGNQ,8608
|
79
76
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
80
77
|
sglang/srt/debug_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
81
|
-
sglang/srt/debug_utils/dump_comparator.py,sha256=
|
82
|
-
sglang/srt/debug_utils/
|
83
|
-
sglang/srt/debug_utils/
|
84
|
-
sglang/srt/
|
78
|
+
sglang/srt/debug_utils/dump_comparator.py,sha256=3rWdv4BQXTDtB3z5ao9VPN5lK31ImKf2zMWX7f0Xe6s,5394
|
79
|
+
sglang/srt/debug_utils/dump_loader.py,sha256=RzWpl7RsDRw98DJMEvf6U9c9fPiobyeWI8opmRaRGGA,2632
|
80
|
+
sglang/srt/debug_utils/dumper.py,sha256=yqxsa_I_DoCeHkDoXDgFXO0AcBzXSkPMFJ2JG73PSRA,3291
|
81
|
+
sglang/srt/debug_utils/text_comparator.py,sha256=NLJdjUikW--bWnGQWIeFJesyuvZ2Vni2S53fIED-m8s,7370
|
82
|
+
sglang/srt/disaggregation/decode.py,sha256=oAI4R3kzUqNQHUcMh9mZ-d9IB9ApV1s9bkRCN-RvHos,34659
|
85
83
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=Iu7ehHGAfYIVATtClwX6y-6zxWs-JyDlMotYo_5yuUc,6598
|
86
84
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
87
|
-
sglang/srt/disaggregation/
|
88
|
-
sglang/srt/disaggregation/
|
89
|
-
sglang/srt/disaggregation/
|
90
|
-
sglang/srt/disaggregation/utils.py,sha256=evdv4AkQxJzTqdO0jrdAr7vHUbBSCEXMzNREh0FoRLc,12294
|
85
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=JY2uCeUM3Zk3FdGWmCQBY3LeiJ5FM1PlrqAW8wJTTHI,395
|
86
|
+
sglang/srt/disaggregation/prefill.py,sha256=jgZN8YmgL4wGSN2GDV88sUHfSyG3bpLg3Cb3kbEGzgo,36350
|
87
|
+
sglang/srt/disaggregation/utils.py,sha256=DvE3nj8GdoD4N_1rSpP1R2gSV4wEMWRACqfmxR27qhg,10898
|
91
88
|
sglang/srt/disaggregation/ascend/__init__.py,sha256=-lxnica6fZYmYNpKwmE8yESUpQ5Sxf2DiZoBHzboKc8,146
|
92
|
-
sglang/srt/disaggregation/ascend/conn.py,sha256=
|
89
|
+
sglang/srt/disaggregation/ascend/conn.py,sha256=EuCsFMxwxDp7jt8K2uyTtRlIk0Vi5A_VBz6hKYwybhU,4119
|
93
90
|
sglang/srt/disaggregation/ascend/transfer_engine.py,sha256=_4PszsQL6wICdg5cqpR2N9TbZpUY6bBX8tgE3xeaYfc,2137
|
94
91
|
sglang/srt/disaggregation/base/__init__.py,sha256=4VwUv0aWxwmVL1049XK82aLTNxmt0WY5RPy9li-wyVk,160
|
95
|
-
sglang/srt/disaggregation/base/conn.py,sha256=
|
92
|
+
sglang/srt/disaggregation/base/conn.py,sha256=0CGEv-B24woyDBdEgQwT8Gqz10Uox3gCgWiCxznXkwQ,2912
|
96
93
|
sglang/srt/disaggregation/common/__init__.py,sha256=7yl-EGLMVKRpBUaGF_7lwAsw2J_mqpRZV0238VGxD9o,126
|
97
|
-
sglang/srt/disaggregation/common/conn.py,sha256=
|
94
|
+
sglang/srt/disaggregation/common/conn.py,sha256=_f4JfgffnV0wThhKVhBUGhRt-_smQBE6WwyPAo0C84s,17190
|
98
95
|
sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeKVPMWPcB5ywbE,1194
|
99
96
|
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
100
|
-
sglang/srt/disaggregation/fake/conn.py,sha256=
|
97
|
+
sglang/srt/disaggregation/fake/conn.py,sha256=qsN5SEQLMenALxYC3x7GYZprhUQyRje5ldNwjkT6OPw,2283
|
101
98
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
102
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
99
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=27UIE4ha8ELORhkPZec26LLGN_gEhlazyu1EeWDxwwc,71702
|
103
100
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=O-XRmQ3QwD6RuiyRgw4ZohSrFkuPdppV_eDBMUXn0jk,5884
|
104
101
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
105
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
102
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=AEyQ_k-LQ3rBVubdbqZ_9XCZ8xoX9ORpOdQVwY3istU,27010
|
106
103
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
107
104
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
108
105
|
sglang/srt/distributed/naive_distributed.py,sha256=5Kcfapzz61G3TtScTZrHoWa4bf6Vr27GlMcBAGMz7tQ,3260
|
109
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
106
|
+
sglang/srt/distributed/parallel_state.py,sha256=goztGivgPYGRG6uOIMnPMYKx_CdQquKLQO2m8gcpS-0,66530
|
110
107
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
111
108
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
112
109
|
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=Q1kkKPKFPV0QMmKLyjOBlOnX8-Pr4UeGBZYkG6j0gc0,16570
|
@@ -122,29 +119,29 @@ sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=IrSrnpZnii0E
|
|
122
119
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
123
120
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
124
121
|
sglang/srt/entrypoints/context.py,sha256=aD-94xkD0komuGO5gtYUoJKCHdc4hAipMxQt04yVRGA,8030
|
125
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
122
|
+
sglang/srt/entrypoints/engine.py,sha256=dxgDwG14iN08SAYm9nB_3nx3d9oGHc_Bwxj7rZT_Bko,33834
|
126
123
|
sglang/srt/entrypoints/harmony_utils.py,sha256=01T-A5GBUm2b306PcxNEg2rfx4cykBcqNYrzcXTWBlc,13590
|
127
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
124
|
+
sglang/srt/entrypoints/http_server.py,sha256=urdEcQ7PHL_-4Ip2vm1THr3Vdq1cb7Po9HnVcfMUFoI,49144
|
128
125
|
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
129
126
|
sglang/srt/entrypoints/tool.py,sha256=aAXEjBqkr5j6_IgRL8fZCKgoDPY2TikM20-LQXU9TaI,2709
|
130
127
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
131
|
-
sglang/srt/entrypoints/openai/protocol.py,sha256=
|
132
|
-
sglang/srt/entrypoints/openai/serving_base.py,sha256=
|
133
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
134
|
-
sglang/srt/entrypoints/openai/serving_completions.py,sha256=
|
135
|
-
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=
|
128
|
+
sglang/srt/entrypoints/openai/protocol.py,sha256=CLFG9mE1WL5G4xomK-frtYxXSNfq0lqoCLisYESvMlw,28737
|
129
|
+
sglang/srt/entrypoints/openai/serving_base.py,sha256=wl6_lFoG5XdCTwgbaeKvPnLeWLmLtM-0wSI9vRiZvYA,5519
|
130
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=FzoJ2fL6CF0IzUWUErnPLKhBvbqpHIaZy2W7zuRSi-w,43380
|
131
|
+
sglang/srt/entrypoints/openai/serving_completions.py,sha256=yoD0ka5qHaQF2_iQjadM-x4AXYDSjPxQAYdq_umvJ5o,17938
|
132
|
+
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=8s_c0H_YA88xoDXcIprsCKm_q3aPt3HM64bsCSCmZZQ,6359
|
136
133
|
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=8n6y5kC6UhRpWrDtzH0eIp0dznW12FT60MLCR4bvD2U,3333
|
137
|
-
sglang/srt/entrypoints/openai/serving_responses.py,sha256=
|
134
|
+
sglang/srt/entrypoints/openai/serving_responses.py,sha256=DnNGNJqmHu4ZB52p9jTxneASgTSEl14fCUGUBWx46B0,53482
|
138
135
|
sglang/srt/entrypoints/openai/serving_score.py,sha256=ebAts-m6Pq-LTgFKwggkywBUrAgUSppHHVEzgwYHUzo,1955
|
139
136
|
sglang/srt/entrypoints/openai/tool_server.py,sha256=rRNGELPV5RHONp55MYkO4_b0NPsPffJnWg-gMYwDSTc,5659
|
140
137
|
sglang/srt/entrypoints/openai/usage_processor.py,sha256=9LTB5rqdRuMKyZrIXiUBuF_WKaSg9X45YdzERDxbtCY,2746
|
141
138
|
sglang/srt/entrypoints/openai/utils.py,sha256=DT9quW0F1DX1P9NAuMxpERgXcNYKKtm7rd7J1m7EaDQ,2112
|
142
139
|
sglang/srt/eplb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
143
|
-
sglang/srt/eplb/eplb_manager.py,sha256=
|
144
|
-
sglang/srt/eplb/expert_distribution.py,sha256=
|
145
|
-
sglang/srt/eplb/expert_location.py,sha256=
|
140
|
+
sglang/srt/eplb/eplb_manager.py,sha256=e8HMGzZb2QFRGdS7JZIFSy8cOIlxOlGRY-ef7Wei0Sw,4364
|
141
|
+
sglang/srt/eplb/expert_distribution.py,sha256=gd3PktGCSqHLjB5XHhTSA-OtaDVYw-taExCe7NOHM9E,32939
|
142
|
+
sglang/srt/eplb/expert_location.py,sha256=UX87bd00DXOs53ugCiZzqias1ir51dn1KevWpIDAiRc,17155
|
146
143
|
sglang/srt/eplb/expert_location_dispatch.py,sha256=vA0o-7bXf847BQAVCqElWKEpofZLAIsir_d0pew2KNQ,4178
|
147
|
-
sglang/srt/eplb/expert_location_updater.py,sha256=
|
144
|
+
sglang/srt/eplb/expert_location_updater.py,sha256=ScoyCJbtJNQLriQXJNZTV2-5G8-tR3AocZDK3ujMaJk,21172
|
148
145
|
sglang/srt/eplb/eplb_algorithms/__init__.py,sha256=c6fo4qM8N0p5DyyfGp9fxqc2wkxvzSJBzJFRG1I1leg,1959
|
149
146
|
sglang/srt/eplb/eplb_algorithms/deepseek.py,sha256=mMZT7zAAArccdRS0xXxifvMb3qn9enSt426uUTKeiq4,8340
|
150
147
|
sglang/srt/eplb/eplb_algorithms/deepseek_vec.py,sha256=Vzy5Iarua1VgVHzjBNZaVV_vt1LY1BLtJz7PmzB701k,10654
|
@@ -152,83 +149,107 @@ sglang/srt/eplb/eplb_simulator/__init__.py,sha256=HIZaXqsvsOCMMJ81dSs1afSGZ5G6Oi
|
|
152
149
|
sglang/srt/eplb/eplb_simulator/reader.py,sha256=OlsWqsuXqVQY7PfvvrP-vsl2Ww2Kg4vD_K9BltM_QHo,1828
|
153
150
|
sglang/srt/function_call/base_format_detector.py,sha256=FKBzsGFHfNl3Wvccsdvv9ftjbCZIyyjOLj2kHgKvX9g,15901
|
154
151
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
152
|
+
sglang/srt/function_call/deepseekv31_detector.py,sha256=hpRjjv219mH0v1PQpMvj_gezrP7PwvLiNbBKOTCSC3U,9731
|
155
153
|
sglang/srt/function_call/deepseekv3_detector.py,sha256=DhO3tUX1nvFlfRkHJ1Vm_7OMXFFTvWBA9u9SZKFAwuQ,9710
|
156
|
-
sglang/srt/function_call/ebnf_composer.py,sha256=
|
157
|
-
sglang/srt/function_call/function_call_parser.py,sha256=
|
158
|
-
sglang/srt/function_call/glm4_moe_detector.py,sha256=
|
159
|
-
sglang/srt/function_call/gpt_oss_detector.py,sha256=
|
154
|
+
sglang/srt/function_call/ebnf_composer.py,sha256=OpjfvYowLlMLnxz5fwS7zv5-d43_ZwO9ucGAMsILvm4,15321
|
155
|
+
sglang/srt/function_call/function_call_parser.py,sha256=55bbToi2wWGmahfyDX1YeFpndNCwTa23ZdNsawMidbc,8333
|
156
|
+
sglang/srt/function_call/glm4_moe_detector.py,sha256=2mxC4c93lUimNFcho3lAfj54Qm-evRph_NMCpH3H5B4,6941
|
157
|
+
sglang/srt/function_call/gpt_oss_detector.py,sha256=HLthoD4NHl3EKM04R5UL0CvQEYuwFtwtGH8DwHRTCoY,8306
|
160
158
|
sglang/srt/function_call/kimik2_detector.py,sha256=u6GXTAcvqWstkuDgxZMeKlpp9zu3V4OTZ8yaplLxEGM,10109
|
161
159
|
sglang/srt/function_call/llama32_detector.py,sha256=trZja7IXc2IWUko5PRj7p4pRU6XCVjtxr-7qJNr0EWo,3647
|
162
160
|
sglang/srt/function_call/mistral_detector.py,sha256=Ts2HrJdu5r2lCCMVKPZfnCds9pt1K5H1EaOQrF_HD60,4686
|
163
161
|
sglang/srt/function_call/pythonic_detector.py,sha256=yAatItKtVDf9uhlB78wPWKP3fbefLJDNGGzFV5ey-YA,8756
|
164
162
|
sglang/srt/function_call/qwen25_detector.py,sha256=nv83_sipZMU6Vie3J4HeNiZVCSRU5ei7601j50779HA,5181
|
165
|
-
sglang/srt/function_call/qwen3_coder_detector.py,sha256=
|
163
|
+
sglang/srt/function_call/qwen3_coder_detector.py,sha256=fyiF0WkNwozlKZQy0G903hj-ZAyvEgkFC8l20FVOVX8,14299
|
166
164
|
sglang/srt/function_call/step3_detector.py,sha256=SAibrispu0peDQzqOG2-V93KGHtV6Ud7a38vlnhTunA,17442
|
167
165
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
168
|
-
sglang/srt/layers/activation.py,sha256=
|
166
|
+
sglang/srt/layers/activation.py,sha256=ZDEexLd-fmBoe20VoN8UMCEJWzi5rbN6C6LhTfvrZqg,9017
|
169
167
|
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
170
|
-
sglang/srt/layers/communicator.py,sha256=
|
168
|
+
sglang/srt/layers/communicator.py,sha256=NYP2IGKs5eK4X9DNG0MBbKShI1fmT2TExOOuCXR8Nlc,24111
|
171
169
|
sglang/srt/layers/dp_attention.py,sha256=35GQIpO8HpF9mtLQSJe2RW2a5rblTLvzAbr1CL0PbSg,15286
|
172
170
|
sglang/srt/layers/elementwise.py,sha256=PjYv7Sk-zKbG9WiGlYDKsxvNrnxT2N1Q8bA2BWvA1Uo,18771
|
173
171
|
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=hnVVS_VsWukTYhREubWs2KcJ1GjVMEI9ECqxqOMXZv8,6729
|
174
|
-
sglang/srt/layers/layernorm.py,sha256=
|
172
|
+
sglang/srt/layers/layernorm.py,sha256=kPWECOKd8nib3JjbXNIWaCerJdvnbrz3eIpshr5KlrY,11210
|
175
173
|
sglang/srt/layers/linear.py,sha256=f5BZqcbM-6qILXn9nDN2_Vd1Oy8THk0-5z1iw40jRxs,53397
|
176
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
174
|
+
sglang/srt/layers/logits_processor.py,sha256=QFl9-2Ij5Nv2LmVHrGwFjPlGMi3vk-v9e6koDm1WbHg,27191
|
175
|
+
sglang/srt/layers/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
177
176
|
sglang/srt/layers/multimodal.py,sha256=vNswe0J0maeBiN8ehlmxfs-YYlrmMllYl6Nc_Y57Neg,5114
|
178
177
|
sglang/srt/layers/parameter.py,sha256=jCg0G-12GZqTa9gGOqEtVCsnnuBGnYg0VmF6pc6oCFg,17455
|
179
178
|
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
180
179
|
sglang/srt/layers/radix_attention.py,sha256=MpugwaqiY2zPTeg7FVW41OljljCXmYVvHZ2MvneF6PI,3745
|
181
|
-
sglang/srt/layers/
|
182
|
-
sglang/srt/layers/
|
180
|
+
sglang/srt/layers/rocm_linear_utils.py,sha256=7PPh-5H2IYjiLp_g_szzVBsmiMacZ1RtjVtjdrdFJKI,1374
|
181
|
+
sglang/srt/layers/rotary_embedding.py,sha256=0SzOf8SnUbYNxeFLH5tIGuK_Hv0rRONRhRPGZLduxh8,73462
|
182
|
+
sglang/srt/layers/sampler.py,sha256=RIcvSriJaHpFhjNPX3CzJzn4Lwy9H3MTPBeZjqAZq9o,11762
|
183
183
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
184
|
-
sglang/srt/layers/utils.py,sha256=
|
184
|
+
sglang/srt/layers/utils.py,sha256=E7PHisGiD9ZmLS4RWqCUZWxAQJbfc0WaTfRZ37gUlPI,1077
|
185
185
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=x0421kNUgnAb5LnkJR6O67vGZ0ikSD-ThluV3QGsZ_8,22673
|
186
|
-
sglang/srt/layers/attention/aiter_backend.py,sha256=
|
187
|
-
sglang/srt/layers/attention/ascend_backend.py,sha256=
|
186
|
+
sglang/srt/layers/attention/aiter_backend.py,sha256=WUOf8qba_wD7OgoJMKIsXR6_VdZD18alB3FajafBGSc,43887
|
187
|
+
sglang/srt/layers/attention/ascend_backend.py,sha256=eu8QCXFxVRdArBlVWP3mgaFUC0by27qavEw2NU8djSY,23710
|
188
188
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=_vM05ddWy6SaoqWYPR8w5lflSE4MhcVFR271Q9EKK8E,3600
|
189
189
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=PB5BjbJHhmTg_t0kXfarTI6C3pPvKhBAqvCSGGajou0,9846
|
190
190
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
191
191
|
sglang/srt/layers/attention/dual_chunk_flashattention_backend.py,sha256=hCATQEhBATZpPhBMF-cCM9r6nxXA0dr3jOT_hTFS_T0,68656
|
192
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
193
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
194
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
192
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=3Jgapx8tVh2PbPVi6e5TX6eBttdOSm2V53TDbZRixr8,103779
|
193
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=gDfKYL_xuiPhDakjboqGsMcDnf9Tqu41HNxmfTvUaHA,54407
|
194
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=uhltlfRQo3jQEeps2O7X7PHjpb0V_c1OejXTQ5jWeWU,39769
|
195
195
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=5iSic5ho-lkXNas9mR3uLbXbEl-do31gc8gjR7-a79k,20711
|
196
|
-
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=
|
197
|
-
sglang/srt/layers/attention/
|
196
|
+
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=WVC0VOGyVxq3AH-a6gOScfNpijIgxaEOVo5NQLEH5Xo,4823
|
197
|
+
sglang/srt/layers/attention/hybrid_linear_attn_backend.py,sha256=cTH7RgKrcy-KoqOW04FtyURqJrFTRqsd_2Yg3bwblt4,21330
|
198
|
+
sglang/srt/layers/attention/intel_amx_backend.py,sha256=IU_E7HkPrBLfNG2ArhI1ozHZ_pROujUzdI6g2JuToL0,4154
|
198
199
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
199
200
|
sglang/srt/layers/attention/tbo_backend.py,sha256=CBnSDUmDvT-Tbhi9NHNo1LLkgUAcIsWMJgKa-sAIKW8,9318
|
200
|
-
sglang/srt/layers/attention/torch_native_backend.py,sha256=
|
201
|
+
sglang/srt/layers/attention/torch_native_backend.py,sha256=NdWD2ArmS1lQN9mZIbS2rcHueBWColNxvhcLaQGAKGQ,9728
|
201
202
|
sglang/srt/layers/attention/triton_backend.py,sha256=fvcJLaJaM8JE9Q9Nkmn0dzdYnnYlwELCoxQGMoqS9Gk,41858
|
202
203
|
sglang/srt/layers/attention/trtllm_mha_backend.py,sha256=8MxCAzqsNuvO3mhFqTMXCJ0Tt0_82kFbBHie6m0ieDA,27588
|
203
|
-
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=
|
204
|
+
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=CboLWB55_xJsv_kEu5-_LjvONMOAFEKrjFbERZEpFCs,22865
|
204
205
|
sglang/srt/layers/attention/utils.py,sha256=lx_jNw2VwlBe2VnDb1eXRRdN9WArw9rdWHTHqndUEFk,3174
|
205
206
|
sglang/srt/layers/attention/vision.py,sha256=PZUJuswPWvJ34NTtxJkcXnusojDv0pO0UhrsjL4SWYU,20268
|
206
207
|
sglang/srt/layers/attention/vision_utils.py,sha256=6hPPAt8p3SOm7tgHNUesnMLxvQiKbaOM5EK6K-ig5dI,2771
|
207
208
|
sglang/srt/layers/attention/wave_backend.py,sha256=_rjyALSl5huNtIGSe6OJlBrC04LhwBBu62bgjlkavkw,23010
|
209
|
+
sglang/srt/layers/attention/fla/chunk.py,sha256=N8ToAspPlgR7sVJBImzpmlGV6rWsMA7aTaTa1iddcPg,8929
|
210
|
+
sglang/srt/layers/attention/fla/chunk_delta_h.py,sha256=Gf8RgLesGaR9GM4HTB7kDDCVirwR9XvO7O3I1HWdcuY,10681
|
211
|
+
sglang/srt/layers/attention/fla/chunk_o.py,sha256=IZllM88Ap1ztEF9nOSfcx7KmRvmwIwiBMqwT9AjjH-U,4980
|
212
|
+
sglang/srt/layers/attention/fla/chunk_scaled_dot_kkt.py,sha256=wipJDfcYGxMjYiLdoa2z_lyKTd9RVwkacWjIKRFIN1Q,4411
|
213
|
+
sglang/srt/layers/attention/fla/cumsum.py,sha256=beIT2WTSn8Wk_wknoWM3JYQhzmzR1JJwMFzspsXvWng,8374
|
214
|
+
sglang/srt/layers/attention/fla/fused_recurrent.py,sha256=DzMBjjy4owkeqZx98U9OiJEr6ZgzX6guPe-FOAHKNm4,20856
|
215
|
+
sglang/srt/layers/attention/fla/fused_sigmoid_gating_recurrent.py,sha256=rj9exYjnuzLC7xzmse5yGQrp43yJVs5clr_WhSf4eR0,6424
|
216
|
+
sglang/srt/layers/attention/fla/index.py,sha256=kQGcR1doARV324QuA-faNoyo6u8a_wb-DfiPe_bOdhY,1050
|
217
|
+
sglang/srt/layers/attention/fla/l2norm.py,sha256=XOs5nGdWROp3FW4fHSObC8sa_x697yDV0jt5UKuLllE,3783
|
218
|
+
sglang/srt/layers/attention/fla/layernorm_gated.py,sha256=eVRb8Q-KTBvMEtStkoOo53CYHboto-wfyun76NOwWds,9915
|
219
|
+
sglang/srt/layers/attention/fla/op.py,sha256=Qc-zHwZY9-8Aw53AuuzNfpbPBwKgIvVMgtWcfJLl6A4,1695
|
220
|
+
sglang/srt/layers/attention/fla/solve_tril.py,sha256=-Z51hFsLER_Lzn8h21WRUajbVOA1wuu5TSEvaC2AvK8,14405
|
221
|
+
sglang/srt/layers/attention/fla/utils.py,sha256=yBYjW-blAsq_uZxZ961Dub3cUouIvl4DCKV9UqkQSJw,10474
|
222
|
+
sglang/srt/layers/attention/fla/wy_fast.py,sha256=zf6_76vq7yYtn9Ir1Le4RVOKLaPNF_4bNST3ePuH0cU,4407
|
223
|
+
sglang/srt/layers/attention/mamba/causal_conv1d.py,sha256=7NaZVlsSBjvNFP92cn1U11JL8vTuaq0HiyTybDHwOlo,4460
|
224
|
+
sglang/srt/layers/attention/mamba/causal_conv1d_triton.py,sha256=WgkBUew5PVMH9lRPA-mbBpCW_94d30NvuKGHRLes58A,40810
|
225
|
+
sglang/srt/layers/attention/mamba/mamba.py,sha256=lgVITKk4QFJQEsGN2p1a5RDG4bxGwqT0_K_hrK-5Dbw,2489
|
208
226
|
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=JnOtqtPXEgn_T0R4gGCROx1szlAhu_G_ODNKCazz0lE,20554
|
209
227
|
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
210
228
|
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=eYg4xQoH5gBkM7bjzpBIpTdcelvUK3BujJ-8eXRCm70,17108
|
211
229
|
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
212
230
|
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
213
231
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
214
|
-
sglang/srt/layers/attention/wave_ops/decode_attention.py,sha256=
|
215
|
-
sglang/srt/layers/attention/wave_ops/extend_attention.py,sha256=
|
232
|
+
sglang/srt/layers/attention/wave_ops/decode_attention.py,sha256=oJNBG57cySgxtmJe1MSEsZKOIQOXnH0iVAcFO6DUWvY,4732
|
233
|
+
sglang/srt/layers/attention/wave_ops/extend_attention.py,sha256=LyZQQIvFYfcIcObgy_tETK5JxRLgAkOYlF-KhGcGEoA,3877
|
216
234
|
sglang/srt/layers/attention/wave_ops/prefill_attention.py,sha256=viTUit0rxjVV5UahuwmVAhmL66YRFJD4g1YhH_oRBu8,2344
|
217
|
-
sglang/srt/layers/moe/__init__.py,sha256=
|
218
|
-
sglang/srt/layers/moe/cutlass_moe.py,sha256=
|
235
|
+
sglang/srt/layers/moe/__init__.py,sha256=P8OC-pUE5yeEr80QUDqSPwF9a9BAYPuaK7GNlQovsJw,863
|
236
|
+
sglang/srt/layers/moe/cutlass_moe.py,sha256=JKJED-4709ndP5AwhQ7Vi04GJjw5d9Xl_mWOsZPZ3U4,14298
|
219
237
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
220
|
-
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=
|
221
|
-
sglang/srt/layers/moe/fused_moe_native.py,sha256=
|
238
|
+
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=psvH2RhUQkK4oyaSE7xe0EncCqLvNbd_NwR4XHxk79w,7017
|
239
|
+
sglang/srt/layers/moe/fused_moe_native.py,sha256=XzJPM9Z6YQ4ejrMrBFt3l1i7guBcdQTXo9-gT5H8AIA,3479
|
222
240
|
sglang/srt/layers/moe/rocm_moe_utils.py,sha256=07Z99bTV3B-b2Cbm-odhGpx2twxtnVpYvaDMBE1K3LM,4555
|
223
241
|
sglang/srt/layers/moe/router.py,sha256=eUNu_Uz5VB2FOZzZyYuZo5pokCVBS17_fcjHQbmvDSE,12181
|
224
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
225
|
-
sglang/srt/layers/moe/utils.py,sha256=
|
242
|
+
sglang/srt/layers/moe/topk.py,sha256=gte4-yGt2GdN9AFsGFHisvwkcCIC4w4yYdo_NFn3928,31664
|
243
|
+
sglang/srt/layers/moe/utils.py,sha256=iX_plbxGP23Yfp2tAA8Wgohd7dx-DAqzO8Fa4s9L904,5933
|
226
244
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
227
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
228
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
229
|
-
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=
|
230
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
231
|
-
sglang/srt/layers/moe/fused_moe_triton/
|
245
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=poGKusUolwN3cVkX2ZpJlvz9L2q3dURenPuMxgz1XM4,46159
|
246
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=FnGZ_D6OrIVUHGtFIh2O-fENn1AyBeYWCp9RLvNHFGI,30331
|
247
|
+
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=tis0ZJmih7gKHCurbLtY_o-bY3K4MOzQLYLC3ftIOf0,977
|
248
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=mKH6zTTuh_Z8Ceg6d1VWjGBI3iPBn1YfGO6udxIRAtU,23306
|
249
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py,sha256=fFnRcXA6r0gnD_7EQmb8NacQJRJ8YHsmMZw2khlClTQ,7687
|
250
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py,sha256=QOdl5uhZ8--aryXnKObdspKonGcF6Tc_U9o_lC_opo8,27760
|
251
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=ySf8TThrw20Rkflr5JEyXObnKXCDTKaSvGKNEEjzIOE,39723
|
252
|
+
sglang/srt/layers/moe/fused_moe_triton/moe_align_block_size.py,sha256=U93mxPPU2RP7d3QRSvoG3OCtUQIK8YhQfHf1ZGeREmY,3284
|
232
253
|
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk0nPWQelgvi1rV9Z72FetRo6p7E3rsYs,10986
|
233
254
|
"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
|
234
255
|
"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
|
@@ -396,6 +417,7 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
396
417
|
"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
|
397
418
|
"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
|
398
419
|
"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
|
420
|
+
"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
|
399
421
|
"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
|
400
422
|
"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
|
401
423
|
"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
|
@@ -414,53 +436,62 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
414
436
|
"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
|
415
437
|
"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
|
416
438
|
"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
|
417
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=
|
439
|
+
"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
|
418
440
|
"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
|
419
441
|
"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
|
420
442
|
"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
|
421
443
|
"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
|
444
|
+
"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
|
445
|
+
"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
|
422
446
|
"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
|
423
|
-
sglang/srt/layers/moe/
|
424
|
-
sglang/srt/layers/moe/
|
425
|
-
sglang/srt/layers/moe/
|
426
|
-
sglang/srt/layers/moe/
|
427
|
-
sglang/srt/layers/moe/
|
428
|
-
sglang/srt/layers/moe/
|
447
|
+
"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
|
448
|
+
"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
|
449
|
+
"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
|
450
|
+
"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
|
451
|
+
sglang/srt/layers/moe/moe_runner/__init__.py,sha256=Dc4PH6HfzQDjJWL7iuZ-0qh8oRu7OtnH6IEl675pYiU,172
|
452
|
+
sglang/srt/layers/moe/moe_runner/base.py,sha256=GMdFI74BGO5HDjtel5QWI7W4CFix0BHkw_HrjVswhcw,8905
|
453
|
+
sglang/srt/layers/moe/moe_runner/runner.py,sha256=7ZOqDu0r1GY-9ra1VICq4WmH1nJVSQoE5yBXuSUr2CI,2669
|
454
|
+
sglang/srt/layers/moe/moe_runner/triton.py,sha256=YaPqGIX-5y25nxmjF54_ASYbr9Dw4RYze2cNV4cUg-Q,14433
|
455
|
+
sglang/srt/layers/moe/token_dispatcher/__init__.py,sha256=I5I1ySCHbyAW5cFQy9mpuqkSWqLclLmi2AspCkoP8ig,993
|
456
|
+
sglang/srt/layers/moe/token_dispatcher/base.py,sha256=BqqwuSETP47vTaHkUoQWTEeZcAkg0n_Dgka-PkFM4uc,4029
|
457
|
+
sglang/srt/layers/moe/token_dispatcher/deepep.py,sha256=EVnn9rE5k8Rnrl1P6i6-4bX7qDCHhlqq1o39iPSg3U4,23612
|
458
|
+
sglang/srt/layers/moe/token_dispatcher/standard.py,sha256=_OSudEOHA5qHqR5TJqnylQxUYyk7ZnhRMGOf7sMCyt0,1526
|
429
459
|
sglang/srt/layers/quantization/__init__.py,sha256=GmJvVSlkJXf2AmTfWBN6EBrOhhYlxPYNE_eAEXMZfjs,7813
|
430
|
-
sglang/srt/layers/quantization/awq.py,sha256
|
460
|
+
sglang/srt/layers/quantization/awq.py,sha256=YuAkweqSvQQGTGQvg4VpNXevSaJvT8CROpiNzmY_3tQ,26980
|
431
461
|
sglang/srt/layers/quantization/awq_triton.py,sha256=4XwJbRNlFmlvjbMGtWF1Wvk26Kf96162vNEmuI5Kars,11737
|
432
|
-
sglang/srt/layers/quantization/base_config.py,sha256=
|
433
|
-
sglang/srt/layers/quantization/blockwise_int8.py,sha256=
|
434
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
435
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=
|
436
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=
|
462
|
+
sglang/srt/layers/quantization/base_config.py,sha256=ql3kwwnjVzZGh8BUcimMt8K6kFxQtVbR5WgZHXqkOqA,7245
|
463
|
+
sglang/srt/layers/quantization/blockwise_int8.py,sha256=pqSLo4gwazZ4ajdVzyouwh_Z5oVDbWq9wo8RnrMdY8o,13998
|
464
|
+
sglang/srt/layers/quantization/fp8.py,sha256=1Te5ft-yBXgvdcYcJ4LiBcLpukNqizjuUz_02cUxauU,50783
|
465
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=Mgigb6GmF66oCrgjS97IvDDSacNYb0u-VYAf4FChhqM,54849
|
466
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=rfuSEG2PDjYda4twJF1JaUwvpyyA3B0f2N2YVIIlurU,29038
|
437
467
|
sglang/srt/layers/quantization/fpgemm_fp8.py,sha256=dq7rJz-QB9LovmZZLBMK8YJEOr05wjVrtWLmSTkXjYw,7004
|
438
|
-
sglang/srt/layers/quantization/gptq.py,sha256=
|
468
|
+
sglang/srt/layers/quantization/gptq.py,sha256=Qe6XfBWd9aOW7jkLmQR61AjmJRe5MJi6FJvGno1HH4k,39433
|
439
469
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
440
470
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
441
471
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
442
472
|
sglang/srt/layers/quantization/marlin_utils.py,sha256=aM3GU7b7rHNZE-tZjRSrtOaPWzSaMcLxck4he8MlEVI,26344
|
443
473
|
sglang/srt/layers/quantization/marlin_utils_fp8.py,sha256=iSjq-ikPOTU5plrWNTW4MletKLySIrNl5NhQmY6FyAo,12508
|
444
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
445
|
-
sglang/srt/layers/quantization/moe_wna16.py,sha256=
|
446
|
-
sglang/srt/layers/quantization/mxfp4.py,sha256=
|
447
|
-
sglang/srt/layers/quantization/mxfp4_tensor.py,sha256=
|
474
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=O6PbKk9zBVrfEAAs4E7GdLU8YWCSSlGrAU3EugFKP3U,55159
|
475
|
+
sglang/srt/layers/quantization/moe_wna16.py,sha256=uoRhxJ8W_U_VFpbn03YEp0aCjbzqquWwonjuN7KBucw,19117
|
476
|
+
sglang/srt/layers/quantization/mxfp4.py,sha256=i-QaMdDp-tlHdwrmgGiLmzgzNk_xZ3GxivLFa0GcdgY,32708
|
477
|
+
sglang/srt/layers/quantization/mxfp4_tensor.py,sha256=bGeCXlIOhmFZFGWp_lITkIRDEgGUaLpawDvMy1cTOmA,5389
|
448
478
|
sglang/srt/layers/quantization/petit.py,sha256=74Jn0eICq23v_b4rEctDaYTINtbqkdM6IXycT-_FbbI,8954
|
449
479
|
sglang/srt/layers/quantization/petit_utils.py,sha256=-gy4zMhqNoIA1R0n7-5C0efV54jHonCUgPDUUFjGsyM,3245
|
450
480
|
sglang/srt/layers/quantization/qoq.py,sha256=jM96uJfKz3vo1B6SSIrQXNT3vnD3UJrepK2eY-tSQU4,8139
|
451
|
-
sglang/srt/layers/quantization/
|
452
|
-
sglang/srt/layers/quantization/
|
453
|
-
sglang/srt/layers/quantization/
|
454
|
-
sglang/srt/layers/quantization/
|
455
|
-
sglang/srt/layers/quantization/
|
481
|
+
sglang/srt/layers/quantization/rocm_mxfp4_utils.py,sha256=Z4pYWl6ExOXq2qfTHorW16hVbJ-Rk4G8Wrxn_x8boHE,327
|
482
|
+
sglang/srt/layers/quantization/unquant.py,sha256=T8w0mPvtBM1JhGhle6NoDY9C4xfmPWHU_VEJZWSnUNY,16079
|
483
|
+
sglang/srt/layers/quantization/utils.py,sha256=d4eaS4-Z4q3GRgb4HDMr2EoWEdQCefrVdJufK6n_NQY,18509
|
484
|
+
sglang/srt/layers/quantization/w4afp8.py,sha256=WHxSd_cN9xPLjrUywrCsUBHzfAmjDQOHgCVvh8DkPJk,12256
|
485
|
+
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=GMt0-LEoGo4qMEfwuGMJKell-R-eHWFJCzxEtnXNr64,10419
|
486
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=ChRre9mx8GHQ_EM7pnUdgiMsw6pVPCrAMYGS5ANGuuU,36645
|
456
487
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
457
488
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=DsPCI82A4rqI6mjKo-WorIKUweppFV7-16Qku-zW9_g,25897
|
458
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
489
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=tFw8PIF5r8yjdJFt2_3Ou72vUJvgLd3bXFOWdgsCeno,26732
|
459
490
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
460
491
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
461
492
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
462
493
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=VvqVpAr66AlS5IPVuIR5Nu0ESH0oAoKo545jNart6lI,5493
|
463
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=
|
494
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=4cfB6pv7kt8Ek0e88vLyXymSW6VqbAUpIjNt_-KK9-M,6318
|
464
495
|
"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
|
465
496
|
"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
|
466
497
|
"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
|
@@ -614,87 +645,96 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
614
645
|
"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
|
615
646
|
"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
|
616
647
|
sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
617
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=
|
618
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=
|
619
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=
|
648
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=PI9r3PHCMK9EgpoFuBgR4jvokA5sBz8zyC47ps3wet4,8164
|
649
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=8C4xyO58N3Zl8h-fYddUpXDs3mnSqjYbaLt12cPB2XA,778
|
650
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=qiUuQn-InDLYVNDPFOxde2XB-qlE0fol0HPTkY5KN8g,3197
|
620
651
|
sglang/srt/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
621
652
|
sglang/srt/layers/quantization/quark/quark.py,sha256=EqQvWzAc6nd_yl6UIMIwmozKif4I8fRNfBum040UUEQ,14613
|
622
|
-
sglang/srt/layers/quantization/quark/quark_moe.py,sha256=
|
623
|
-
sglang/srt/layers/quantization/quark/utils.py,sha256=
|
653
|
+
sglang/srt/layers/quantization/quark/quark_moe.py,sha256=e2bVOYrdc7Tlko_B3XucXih-ZGHLgbgyg8oxJWsMEBE,6982
|
654
|
+
sglang/srt/layers/quantization/quark/utils.py,sha256=zZHRe9mjxGp16_OJ5Qy_UtnQgipl3ZRZUmruYvyEm_w,7445
|
624
655
|
sglang/srt/layers/quantization/quark/schemes/__init__.py,sha256=z1LHBPqkxAS6Wp70DWwESOSixWpIhIQwz1IHcWDdURQ,167
|
625
656
|
sglang/srt/layers/quantization/quark/schemes/quark_scheme.py,sha256=b8-Djo-UQAwgxSWViKDoEP5dOSesnEBPyozX-osB3WY,1478
|
626
|
-
sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=
|
627
|
-
sglang/srt/lora/layers.py,sha256=
|
628
|
-
sglang/srt/lora/lora.py,sha256=
|
657
|
+
sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=sW57dU7HoxQGVbzUhyhRirGWA8oVpENB4NTzO7URGgU,4198
|
658
|
+
sglang/srt/lora/layers.py,sha256=0XlVcBTT1InMsBoLfiOO7yOnlDrnpXD_08wKo84T4B4,11852
|
659
|
+
sglang/srt/lora/lora.py,sha256=2PaloPsDIYT5f7alwWEpEMY6H4lOnSprc7Qp3f0KrS0,7554
|
629
660
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
630
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
661
|
+
sglang/srt/lora/lora_manager.py,sha256=A5eXAik7_7Xs_THp5T21ft7gCvUXVVZtJXd7qdrqUL4,18811
|
631
662
|
sglang/srt/lora/lora_registry.py,sha256=osbau-sQZ7BuCeGGpBMFy4w40GO5FGqRgRwDyxxgNmg,8167
|
632
|
-
sglang/srt/lora/mem_pool.py,sha256=
|
633
|
-
sglang/srt/lora/utils.py,sha256=
|
634
|
-
sglang/srt/lora/backend/base_backend.py,sha256=
|
635
|
-
sglang/srt/lora/backend/triton_backend.py,sha256=
|
663
|
+
sglang/srt/lora/mem_pool.py,sha256=KrjMo91sU_SVF9hLHlgzYTVR6KAtOPGzey3CMKL3tkU,11479
|
664
|
+
sglang/srt/lora/utils.py,sha256=_nyVUkH23v38vaMjZoORFfJtD02iCKaHr3rrNUOXezo,4263
|
665
|
+
sglang/srt/lora/backend/base_backend.py,sha256=e88u2MgQ1wE4VoZHyvtnvXsiSYczPyQq3Uiyi0Yn8p4,6145
|
666
|
+
sglang/srt/lora/backend/triton_backend.py,sha256=xX6H5yaTynQ64ipkmU1987vz5u8_ompaAjXdLSB4AbI,5974
|
636
667
|
sglang/srt/lora/triton_ops/__init__.py,sha256=JGOYPIn1XbGcyJTbt8A0qoc02PYONSGNNjGkC8yJpAM,283
|
637
668
|
sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=QURCYxHNR8Ls4SQtt3dvdgjvdDVhywI9tOzsK8SV9m8,5779
|
638
669
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=z9BB84Xu_MjwCu5v9Yvji-FkIzfEjDySAFybc4WYv7A,6483
|
639
670
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=Ksova04wgeGsFqGOXWqJtMYaHgyUYcx8VU42BZQOkVA,5129
|
640
671
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=VqCAFvUtq_l-0RGIkx3W_fzD55QcW2FAcqpvSHOBFp4,5115
|
641
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
672
|
+
sglang/srt/managers/cache_controller.py,sha256=pcbSBo0pFPRFGM_9K8EVx7VVDRAZBmGD866WC2NRves,33301
|
642
673
|
sglang/srt/managers/configure_logging.py,sha256=8sNXZ2z9pBWOwn-X3wyz013Ob8Nbm1zDxRkxoZjH-l4,1633
|
643
|
-
sglang/srt/managers/data_parallel_controller.py,sha256=
|
644
|
-
sglang/srt/managers/detokenizer_manager.py,sha256=
|
645
|
-
sglang/srt/managers/
|
646
|
-
sglang/srt/managers/
|
674
|
+
sglang/srt/managers/data_parallel_controller.py,sha256=PMiE0hkhEEejy9HbLIUZeRFa_H9G5Ar6zKCjwPPt5vI,14790
|
675
|
+
sglang/srt/managers/detokenizer_manager.py,sha256=fO1xY2x8was6pFBAWyiUUDtF0a5E35Z4uGsHe4pPOS4,11785
|
676
|
+
sglang/srt/managers/disagg_service.py,sha256=7VyRva5oniAPs8G-DYg2fv-mdjSxk9cLZPzl_TmB_2Q,1588
|
677
|
+
sglang/srt/managers/io_struct.py,sha256=XVbHkPbD7-IuW3d9mU8yE3VFdNGr-dXCl6oDTxure8E,45219
|
678
|
+
sglang/srt/managers/mm_utils.py,sha256=-gElspd-PTWx8k3uuIm83Lb8QXD_dGY5_1WDovKMBKM,29506
|
679
|
+
sglang/srt/managers/multi_tokenizer_mixin.py,sha256=oVLgbz40ly3GJxah_tF6_s0pT_OdHnRtrBzESPLFVY0,21616
|
647
680
|
sglang/srt/managers/multimodal_processor.py,sha256=cnWpu2G79v1a6FJB_FriLxESgGUbfC3GptLmeRVVgew,1801
|
648
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
649
|
-
sglang/srt/managers/schedule_policy.py,sha256=
|
650
|
-
sglang/srt/managers/scheduler.py,sha256=
|
681
|
+
sglang/srt/managers/schedule_batch.py,sha256=XFw8jcHlf0X9rH8O7NIjpty6VE3PlmnIvg3x-0jEudE,76557
|
682
|
+
sglang/srt/managers/schedule_policy.py,sha256=ae3XqkItQpcBxOGaWmXRh-kqYtJRegr44SGqX74g918,22454
|
683
|
+
sglang/srt/managers/scheduler.py,sha256=ObMJFSSb697ybUtzZe5t-lLowKZoFBr7-6GVho-iOsc,108517
|
651
684
|
sglang/srt/managers/scheduler_input_blocker.py,sha256=zP8xU_UmU2H0AB6sEqvivDcDB1QDgTauNDYDIJ7Nez4,3683
|
652
|
-
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=
|
653
|
-
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=
|
654
|
-
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=
|
685
|
+
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=IQXmFPdP73mneVNrWgxJ-UxFeb_DVGWBYp3wr0lvbGk,14612
|
686
|
+
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=4mE5-LAbzHjiR8t8sHuP70ySL8LuYNxi_KK8qOXWNrg,31764
|
687
|
+
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=4-slXlOPo8AMD8nkvASmA2hov_-dX2a2CvVd0AKFTTM,11403
|
655
688
|
sglang/srt/managers/scheduler_recv_skipper.py,sha256=8rVQCBjn9f26Th4XbeUS3fEsvo1GI029Me28wMjcKRY,1103
|
656
|
-
sglang/srt/managers/scheduler_update_weights_mixin.py,sha256=
|
689
|
+
sglang/srt/managers/scheduler_update_weights_mixin.py,sha256=uk7Dusr8EJBDRdcuQNIoedj0oP4tmSWrUbEqmjclwnk,5813
|
657
690
|
sglang/srt/managers/session_controller.py,sha256=FGADRGSkRmS76o_BQ2fivpgw0Q5Q-K0Ws3aezH41YSc,6041
|
658
|
-
sglang/srt/managers/template_manager.py,sha256=
|
659
|
-
sglang/srt/managers/
|
660
|
-
sglang/srt/managers/
|
661
|
-
sglang/srt/managers/
|
691
|
+
sglang/srt/managers/template_manager.py,sha256=M4EshVv1OhKxUAGQPP4OntRkSkUVvG93457xsYfWnQk,11968
|
692
|
+
sglang/srt/managers/tokenizer_communicator_mixin.py,sha256=asYlWUc50MSbSOvJaz88rNLl4sv2rqD37pCnLW6dhaM,18323
|
693
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=ouTBGfzfKAHbt4pzf54sU0oag8GCcIc5b2bTxUt23lA,70235
|
694
|
+
sglang/srt/managers/tp_worker.py,sha256=TleRBhJoXCRGUot6VHuCZhftOkjRcfsemCB7Brs0sxc,12426
|
695
|
+
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=VfMxxXj5rSHsrheOz8qwoatR1fCqLwNLf3ySmbFlTYc,10987
|
662
696
|
sglang/srt/managers/utils.py,sha256=WbUdADEdiSOoQNfwjfU64mNaXoskEveBO1HP_t0FJtQ,5687
|
663
|
-
sglang/srt/mem_cache/allocator.py,sha256=
|
697
|
+
sglang/srt/mem_cache/allocator.py,sha256=47M3lrAv9k2MJXQc82oGXokLb_3u1A8LFNL9WmgIBN8,18219
|
664
698
|
sglang/srt/mem_cache/allocator_ascend.py,sha256=i0KPCcFlzGkCIjW8ph3IPkBXAWTqq4-AeaoG1wR--lw,4471
|
665
699
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=hLS2ncTMAz7Kpdk5pNwn5c6g8b61_K9OCBL4Vj1xsYc,2801
|
666
|
-
sglang/srt/mem_cache/chunk_cache.py,sha256=
|
700
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=jbJeEEZ5_WYEF_AnDZIAu2sMD4hAGAd_24F980fjVwU,3199
|
667
701
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
668
|
-
sglang/srt/mem_cache/hicache_storage.py,sha256=
|
669
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
670
|
-
sglang/srt/mem_cache/lora_radix_cache.py,sha256=
|
671
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
672
|
-
sglang/srt/mem_cache/memory_pool_host.py,sha256=
|
702
|
+
sglang/srt/mem_cache/hicache_storage.py,sha256=o9__S2_pH6FZOXUMvDbKSxzuCzFZd7SnBPlU92YIIWY,6990
|
703
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=96t0FUcrjee8ScjxFXmw_SXAjB90vxo0LvPvzEBgSB0,31913
|
704
|
+
sglang/srt/mem_cache/lora_radix_cache.py,sha256=4NbK0Rc15kTiCOSsthyM6WsZarMK2MNhtsNqYMakJ5k,14369
|
705
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=CRSSLeuedQJOIR6TOaKKSgvr79_cf3ypVx1_ovM1fLA,49716
|
706
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=l-Po0WxpaOdLjxmfGy4DCiZxjkkHZRja2p3kwwoJJkM,26503
|
673
707
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=zPnQLQhBZ6zsUpCQPSoNkrB9EEvpoDQS4mU7c3sRWjE,2171
|
674
|
-
sglang/srt/mem_cache/radix_cache.py,sha256=
|
675
|
-
sglang/srt/mem_cache/radix_cache_cpp.py,sha256=
|
676
|
-
sglang/srt/mem_cache/swa_radix_cache.py,sha256=
|
708
|
+
sglang/srt/mem_cache/radix_cache.py,sha256=WrzDSfUdyctshXQ1hN3LKpH-DCY2-dZ8xzmc2Iy6jeE,19027
|
709
|
+
sglang/srt/mem_cache/radix_cache_cpp.py,sha256=YuYt4xNzfmNNSkwaAk3VLWcZI74_XQobIyEgt96f7Qs,9284
|
710
|
+
sglang/srt/mem_cache/swa_radix_cache.py,sha256=m0MAXw8bpY4nRWvU4qEWR8UzjgoqrYZSsy4aF5fWsKw,40226
|
677
711
|
sglang/srt/mem_cache/cpp_radix_tree/radix_tree.py,sha256=tQZpz-H6HxNAQe9mYqt6aX8mfDZyu_fbJTcCNK-Ns1M,7179
|
678
|
-
sglang/srt/mem_cache/storage/hf3fs/
|
712
|
+
sglang/srt/mem_cache/storage/hf3fs/hf3fs_client.py,sha256=le_iTE5HZAbQNToa5E_dq_3U5ztu60ej-58tmzRtndM,5245
|
713
|
+
sglang/srt/mem_cache/storage/hf3fs/hf3fs_usrbio_client.py,sha256=6oH4v_WF_pKH4FMSr252v6QPhBCnRHztHqzuS8j6_QI,5323
|
679
714
|
sglang/srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp,sha256=dDYPtxmL6OFhEyv_GuTgzkTDpBjcD0EK8kphnn7eaGc,1133
|
680
|
-
sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py,sha256=
|
681
|
-
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=
|
715
|
+
sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py,sha256=lJ9Jp2kOgQQaUihxlO9l-W8fYfOMa1h1y0WAtzzFGLM,17850
|
716
|
+
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=ujsS5VMF8hZtlJDk3ye0atstEcyhPoN8vHnMYCDnAgk,17977
|
682
717
|
sglang/srt/mem_cache/storage/hf3fs/test_hf3fs_utils.py,sha256=g2h0Woa2CK39pRTigHCVR_hq095dTaC70lCIAIs9THM,1089
|
683
|
-
sglang/srt/mem_cache/storage/
|
684
|
-
sglang/srt/mem_cache/storage/
|
718
|
+
sglang/srt/mem_cache/storage/lmcache/lmc_radix_cache.py,sha256=2G9qyIiQbBaDanAFQEL_2-DoQA7F-B_rVP3INXCXb0E,9764
|
719
|
+
sglang/srt/mem_cache/storage/lmcache/unit_test.py,sha256=DCSZDMJAe-HehL9hWzsP759pck36Q-8ijxWZKfgXmA8,3590
|
720
|
+
sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py,sha256=CM3lp6HOcYKGqZYkhgugKNH7ZO4_gn_EGZkgczlOLdw,12215
|
721
|
+
sglang/srt/mem_cache/storage/mooncake_store/test_mooncake_store.py,sha256=6TiqbzEIL71DC7wL1B-Q-SMMZRYsz08sg-dZYeMzmAc,4930
|
685
722
|
sglang/srt/mem_cache/storage/nixl/hicache_nixl.py,sha256=bau9Jsp50lpEiy_osgb-dYzeoUkPWM03x7Q8z2BpKaU,9920
|
686
723
|
sglang/srt/mem_cache/storage/nixl/nixl_utils.py,sha256=KXkwMrbWwIOUOASINnUo4HyheiMd-93smmwGLv0CacU,7463
|
687
724
|
sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py,sha256=vENVvGAd3PqcQEFA812wPoSBYhRemLr8Sfh1LQa0INU,9609
|
688
|
-
sglang/srt/metrics/collector.py,sha256=
|
725
|
+
sglang/srt/metrics/collector.py,sha256=IWdyE3GBpoxFEuUmCHh3-48gXJiAQ7AhsO53ImuQ4RE,35077
|
689
726
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
690
|
-
sglang/srt/
|
691
|
-
sglang/srt/
|
692
|
-
sglang/srt/model_executor/
|
727
|
+
sglang/srt/metrics/startup_func_log_and_timer.py,sha256=PRVg3Z2d5GBMFifZXR-VhzGcn9nmKTkqEU41VJKZmaI,4937
|
728
|
+
sglang/srt/metrics/utils.py,sha256=BkLQFOfzNknDJ5zc4wOqkJ9awLuQE7EtwA0EYjlJg7I,1715
|
729
|
+
sglang/srt/model_executor/cpu_graph_runner.py,sha256=lwh4RL4K3wPyCIz4lA_J7CtPZt4L0rxDLJcg8uNrzpc,23410
|
730
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=aOC4sKZj1wqAAVTLncRnlOsE1nujBF_z8GaUczeDt-I,34143
|
731
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=wv8AWG3GHzBP0idqMZ_dhigVM5HDV0v8gKFtWbAscBY,42811
|
732
|
+
sglang/srt/model_executor/model_runner.py,sha256=D4cGCNhrB1WXdCEQPs2_nGUh17e2KyldL3Xk4bHePrI,85356
|
693
733
|
sglang/srt/model_executor/npu_graph_runner.py,sha256=isp2Plkf4b_gdjptYxJhTJk7JL21Jg-Md3hAYIuSVxM,3424
|
694
|
-
sglang/srt/model_loader/__init__.py,sha256=
|
695
|
-
sglang/srt/model_loader/loader.py,sha256=
|
696
|
-
sglang/srt/model_loader/utils.py,sha256=
|
697
|
-
sglang/srt/model_loader/weight_utils.py,sha256=
|
734
|
+
sglang/srt/model_loader/__init__.py,sha256=_1Y5sUZGxEEG_bmvLbSgYGa__qO60_d0blGB8sIdOgo,1020
|
735
|
+
sglang/srt/model_loader/loader.py,sha256=oGBbQM49HAW8P1j_YY4pndAqb7wha-Sl6Aetqo5Wpno,60312
|
736
|
+
sglang/srt/model_loader/utils.py,sha256=KrOpyd_eefZC3zFnhnwxIKNTx9G-MmA6jIK3NQbTW0E,5002
|
737
|
+
sglang/srt/model_loader/weight_utils.py,sha256=mv3a-c0M2ocDiwAtD6h6uvCybL5BM738te_QrbCaQa8,38611
|
698
738
|
sglang/srt/models/arcee.py,sha256=Q6fujRESEnljzs8ls3XGsPtWxzfKfUa0QAvAekYzeBY,18981
|
699
739
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
700
740
|
sglang/srt/models/bailing_moe.py,sha256=1I5xcwtS-y0EOKje7q3j6ORIj8gBuasHS0WmmOCRHIc,14395
|
@@ -706,7 +746,7 @@ sglang/srt/models/dbrx.py,sha256=117gwrB_o8VlACwDH5YlXkPfuS7t2Mh-nyJvpNpIYxs,159
|
|
706
746
|
sglang/srt/models/deepseek.py,sha256=M7nyHcAbTIs8vc1g6u00oy22-pp704Xp4T3clBzu4xM,17460
|
707
747
|
sglang/srt/models/deepseek_janus_pro.py,sha256=td8xGs6ARfJ8AQCYwUhMOZoWigrAs7m3trF5-kXCqik,70418
|
708
748
|
sglang/srt/models/deepseek_nextn.py,sha256=uoiJxAVl9DX7bQcjyuouAZz6W-cB1HMubcirTBghyR4,6115
|
709
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
749
|
+
sglang/srt/models/deepseek_v2.py,sha256=a-2mruSUedmFkOyApIQtkrdu2Oc-uWm4fOwVMQmlpbo,117032
|
710
750
|
sglang/srt/models/deepseek_vl2.py,sha256=7X3gI4DE7guUtNJvMLf06jO8MUHKa2Aan8evZg5hsXc,13061
|
711
751
|
sglang/srt/models/ernie4.py,sha256=7dP7_d0i86tv8Mp21Ew9RdsFr6TskIkm8UtUd8zFo00,16067
|
712
752
|
sglang/srt/models/ernie4_eagle.py,sha256=E7f-ygCcY8pIoyTMKFyVC2uRcG59-_RaQTO4gd5_uWI,7223
|
@@ -718,15 +758,15 @@ sglang/srt/models/gemma3_causal.py,sha256=0FdI0wVoJ4ZakBl8ShO29D1uEMO0T8CRjdsfiH
|
|
718
758
|
sglang/srt/models/gemma3_mm.py,sha256=sRvdAOiStlDhC_-sSH226d0awx4ZQJG7Wtdf7PE6ygw,17189
|
719
759
|
sglang/srt/models/gemma3n_audio.py,sha256=isgKfjA5UieYawxU6medL2ssXlzYPqAbagDBnLcemC0,36405
|
720
760
|
sglang/srt/models/gemma3n_causal.py,sha256=kBDlpSWAg6ZDmUPe08Q7sj5CbdVD_0h07zwJw8sKu7I,36335
|
721
|
-
sglang/srt/models/gemma3n_mm.py,sha256=
|
761
|
+
sglang/srt/models/gemma3n_mm.py,sha256=Kp2Wu-LFoDNU-OHD8Y0tSGGmu9cjkFr-2cHe9wxJ0Kg,20365
|
722
762
|
sglang/srt/models/glm4.py,sha256=dijzVTTgg8zyJ3gga95MKY0WwqwnuAaf-VIV93OFAmc,11433
|
723
|
-
sglang/srt/models/glm4_moe.py,sha256=
|
763
|
+
sglang/srt/models/glm4_moe.py,sha256=X57Pw4O7025eylkSnaSEw3ELfnmlGDt0DCyhD977Bcg,41994
|
724
764
|
sglang/srt/models/glm4_moe_nextn.py,sha256=EuDWOBSd0oFfdvloePlpzAL81M_L7oz0BiWm74RQioc,5943
|
725
|
-
sglang/srt/models/glm4v.py,sha256=
|
765
|
+
sglang/srt/models/glm4v.py,sha256=_yt82CUUasko--6ew7d2hrXtqoxa0nE_4ikPdBL7thI,23755
|
726
766
|
sglang/srt/models/glm4v_moe.py,sha256=qgJtWyRI0dy9qcTMXHxhBZp-ghfghV3PLhpOXgSAW60,17313
|
727
767
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
728
768
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
729
|
-
sglang/srt/models/gpt_oss.py,sha256=
|
769
|
+
sglang/srt/models/gpt_oss.py,sha256=6g7PE6EiOLDipmhV-XKmBcuoCGbhH6SU6NwsSoB_FJM,44469
|
730
770
|
sglang/srt/models/granite.py,sha256=8q92shxVPAp_cJDohJATffSGd7Z0Oi-vF5jpY6DlK4s,19840
|
731
771
|
sglang/srt/models/granitemoe.py,sha256=j1rgZ62CbBioECjUblDCw_NneDQgY_QJODsI0fqXVO8,13779
|
732
772
|
sglang/srt/models/grok.py,sha256=8KCR13LtdnhswJrIwgb0sdFW0OxCA8GQ0fbN8gb856E,40518
|
@@ -735,33 +775,36 @@ sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo
|
|
735
775
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
736
776
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
737
777
|
sglang/srt/models/interns1.py,sha256=E4SyJWocXZ5rAuAV8kj569OHo57r04W4hmq1CF6oiFs,12516
|
738
|
-
sglang/srt/models/internvl.py,sha256=
|
778
|
+
sglang/srt/models/internvl.py,sha256=iQm2wDtkcyjPYoV9oY_jQ3_7WvhP315eP_vZEiQX3uw,27062
|
739
779
|
sglang/srt/models/kimi_vl.py,sha256=XulRiufQzOSWZe8-bUl2OEdznvsVU9OBsEYipaX3YkM,12877
|
740
780
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
741
781
|
sglang/srt/models/llama.py,sha256=tdyUon6icwzqo4XTAkFxVA2f82g80AGr9ZezK1uXmkM,28126
|
742
|
-
sglang/srt/models/llama4.py,sha256=
|
782
|
+
sglang/srt/models/llama4.py,sha256=i4-Vo5FVE9zf_6Y80dyft5VjPOQ-a-xWYfEV8s-ltKQ,19872
|
743
783
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
744
784
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
745
|
-
sglang/srt/models/llama_eagle3.py,sha256=
|
785
|
+
sglang/srt/models/llama_eagle3.py,sha256=lutyS4UaPg5QussPu08En3iO5e1lhsSm4dBXTm4R_XI,9201
|
746
786
|
sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OWYfirZnA,3254
|
747
787
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
748
788
|
sglang/srt/models/llava.py,sha256=xzYip_BAwpzSIdZre43LZiyTpFISa0ZCLdO6LUSbaCg,37702
|
749
789
|
sglang/srt/models/llavavid.py,sha256=-CSk0RJ2MQeb81sh-RISeVJFaI-XWY6nR6_I594MkME,12818
|
790
|
+
sglang/srt/models/longcat_flash.py,sha256=gyElibQ9q_qq4tBA7eah0f3bLSzvMEpgD_n6CcRyG9M,41055
|
791
|
+
sglang/srt/models/longcat_flash_nextn.py,sha256=oVy776-AE5z43C472oqHlcl9NfzDDEaQgGB1msZNdgc,29644
|
750
792
|
sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
751
793
|
sglang/srt/models/mimo_mtp.py,sha256=jSmqJAXu7G3OO7jW1oa2suI4H_Yl7u5ZT7w4lHFbHhg,7292
|
752
794
|
sglang/srt/models/minicpm.py,sha256=CzBJyZtfMpp8jvlEl29DHI7HLVq-CxuqP1UHwxIbaUI,14567
|
753
795
|
sglang/srt/models/minicpm3.py,sha256=Cflu4Tb2hxpjapRBZ5n4kX8a1nnFwffK-M8uHPRUra4,19276
|
754
796
|
sglang/srt/models/minicpmo.py,sha256=st8I13Ere5RkRHHQQN1LgZh1ybUA3_buxaaE4XlV8ag,76123
|
755
|
-
sglang/srt/models/minicpmv.py,sha256=
|
797
|
+
sglang/srt/models/minicpmv.py,sha256=_CnCR2y3RaYxhONAKFpBIuPQBrqn9Od4o7QnJw8CLR4,35884
|
756
798
|
sglang/srt/models/mistral.py,sha256=ni7PppA_5X4ivTnIps3yoEaMEL-G6Gaf9b5hGC1vU5Q,3475
|
757
799
|
sglang/srt/models/mixtral.py,sha256=ohZVFJ75QWuE2kBKD7Sd4fcx9YbbjA7JxnYAsOIfORU,17166
|
758
800
|
sglang/srt/models/mixtral_quant.py,sha256=UUIq7lpUonD9IoGePyl59oJYEcVwT9wUXvtVp5tjQ9Y,15406
|
759
801
|
sglang/srt/models/mllama.py,sha256=OdX7brhyfGiMFPulxF77QOUi-Kcscg3Qo4ipyxzs9yA,39670
|
760
|
-
sglang/srt/models/mllama4.py,sha256=
|
802
|
+
sglang/srt/models/mllama4.py,sha256=k4L6haSwh2L-ql6BRkvthAMJ_aZXkRBn9WwFrBExYaQ,35746
|
761
803
|
sglang/srt/models/nemotron_nas.py,sha256=CoSAKqlbej4Xe30uY4w76iASBqeuJf8-imisDK00zEU,15964
|
762
804
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
763
805
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
764
806
|
sglang/srt/models/olmoe.py,sha256=zryYUQEhEdhd6xcR_HyLV7gHCcKt-HWHeEeIUqmhmcc,16100
|
807
|
+
sglang/srt/models/opt.py,sha256=1fdsQU7yXSN9HEWb0ZVdiAF8wLzAunW4XomIrlHyu2o,23476
|
765
808
|
sglang/srt/models/persimmon.py,sha256=86Duo3HiZqDj9O2UzWbJgUEhQOXzGBUdhUofQhcs1VE,11244
|
766
809
|
sglang/srt/models/phi.py,sha256=n6A1d47MvnR1lmSsZ3TuzXk5kT1Lntj_YQ5uNvR0s5o,10287
|
767
810
|
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
@@ -771,36 +814,38 @@ sglang/srt/models/phi4mm_utils.py,sha256=bW3un4x3SHDvSkAOHQEFO286FGdOPeKhBpJCOmN
|
|
771
814
|
sglang/srt/models/phimoe.py,sha256=EGaKFi02MZP20qFrILA4o2SJ0wb1HoJagFTSqVUbJcQ,19223
|
772
815
|
sglang/srt/models/pixtral.py,sha256=ZkZrV0mEfmbBdgRko2AvsMFZbAVskgp_5a5p1xCSRN0,16835
|
773
816
|
sglang/srt/models/qwen.py,sha256=j0OU3JjznWi_TbayI09yYGM-Obov6mQzJO82Hs0qBGw,11868
|
774
|
-
sglang/srt/models/qwen2.py,sha256=
|
775
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
817
|
+
sglang/srt/models/qwen2.py,sha256=xptcdyvkQKYj0N67h6391hGAzfTxQN1hVhdBfK56FEA,23813
|
818
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=zluJM8KyyjQBV0KfhgdsCcPSKD1QTokhZS7a8JK5w0g,25008
|
776
819
|
sglang/srt/models/qwen2_audio.py,sha256=SOOsspU7J6eM-iSkms5op0nWhoxJd6QxmwXU2aQBEEQ,7776
|
777
820
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
778
821
|
sglang/srt/models/qwen2_eagle.py,sha256=6spFg6JYQGeUXLv2Q5eMkVzZvnqGyvW6SdVBtFMxlTM,4806
|
779
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
822
|
+
sglang/srt/models/qwen2_moe.py,sha256=M0GE6_r-GmEZwuXxCWz9ugcaoukNJkEFbVhj7NCTfT0,28305
|
780
823
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
781
824
|
sglang/srt/models/qwen2_vl.py,sha256=ZRAL32Ymt4ZCBqB0JorXAm4ZBrECZ9EbaXKaTSikkQM,21366
|
782
|
-
sglang/srt/models/qwen3.py,sha256=
|
825
|
+
sglang/srt/models/qwen3.py,sha256=cfp7rL20_E4PyPii85gnXsfsje9b_WK3br-sbYikd0E,19324
|
783
826
|
sglang/srt/models/qwen3_classification.py,sha256=bdjAylXJCjXKjAho74nmtIMpEG0Af98N-aZQ-pKKMY0,3262
|
784
|
-
sglang/srt/models/qwen3_moe.py,sha256
|
827
|
+
sglang/srt/models/qwen3_moe.py,sha256=-Op20J68bwe6-fKsBlif1h2nlASqLHaTxWAxe_xiEuI,33198
|
828
|
+
sglang/srt/models/qwen3_next.py,sha256=hKX-jt-RxSr2tfpsmuVPExRvUDNILYKT9NekYEWzi5g,36366
|
829
|
+
sglang/srt/models/qwen3_next_mtp.py,sha256=YLHNekqQedqhlbil0T2JfVhnHZO6ttUI7miM4tLJgH8,4277
|
785
830
|
sglang/srt/models/registry.py,sha256=kKQ5ruD6_c3JxWsykOoxt-hroSlslv-Niz0nYvHrhGg,3779
|
786
831
|
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
787
832
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
788
833
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
789
834
|
sglang/srt/models/step3_vl.py,sha256=joJmGukbGThLvwwbwrI4mCEVONH_U1dzFLWdpeJFoKo,35654
|
790
|
-
sglang/srt/models/torch_native_llama.py,sha256=
|
791
|
-
sglang/srt/models/transformers.py,sha256=
|
835
|
+
sglang/srt/models/torch_native_llama.py,sha256=qavMy0wjaX18pM7UJscjoOpSKWgDT_INlnImU6OJ4Lw,18327
|
836
|
+
sglang/srt/models/transformers.py,sha256=laA2h39MPeiAWKv4DEg0ydre-1pyXWFSRga-nwy1HUk,10244
|
792
837
|
sglang/srt/models/vila.py,sha256=3NiRHWOqXnCRjXmswAldsNtiE5zRILbScEsbhUzLZF4,9846
|
793
838
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
794
839
|
sglang/srt/models/xverse_moe.py,sha256=nBtG_PAK8wcp1tW2l2Zby2oEOmtWAYzH5COH-_N5IAM,17072
|
795
840
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
796
841
|
sglang/srt/multimodal/mm_utils.py,sha256=6bV1_a7Iet9W0y3qdd0E-hFM78zalIzNZCYbLzJX2y8,12640
|
797
|
-
sglang/srt/multimodal/processors/base_processor.py,sha256=
|
842
|
+
sglang/srt/multimodal/processors/base_processor.py,sha256=G25SF9bIyoQ13v7Qsb2ZDWTBq-BJ8Sa9okGZPPsS2TM,24518
|
798
843
|
sglang/srt/multimodal/processors/clip.py,sha256=5nXZuQYbyf-5mlqPwjhQrlWqxvswImWZQXivChsiHfQ,1057
|
799
844
|
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=Pymag9f0U5L_bBOTFs2q94BbuPJ-VwqSixs3meO0nsM,2569
|
800
845
|
sglang/srt/multimodal/processors/gemma3.py,sha256=7aD6cR60iSC_MqjzdCDMAgtrb_cmy9YJyqLgVRClBT8,1986
|
801
846
|
sglang/srt/multimodal/processors/gemma3n.py,sha256=mtmvBasOMxb3Y2NLZR02nMYX30RLUXhDYJ5uVOElr10,2776
|
802
|
-
sglang/srt/multimodal/processors/glm4v.py,sha256=
|
803
|
-
sglang/srt/multimodal/processors/internvl.py,sha256=
|
847
|
+
sglang/srt/multimodal/processors/glm4v.py,sha256=SQXatu6t-YgE8wNSavBRliN7J4DqiP57lmA47-zRlYQ,4953
|
848
|
+
sglang/srt/multimodal/processors/internvl.py,sha256=1fYa9MdbxJnKc9vfUiyqxsiO0H_aaW3uUI1-0LoXKHo,9976
|
804
849
|
sglang/srt/multimodal/processors/janus_pro.py,sha256=_4ltWmdtFjbh1VCMRbcgxW61eWIABIzHG-YgwHWaYq8,1471
|
805
850
|
sglang/srt/multimodal/processors/kimi_vl.py,sha256=5i8KmGxnnDtQc7XqUBNyanAfGxhxj8iRFBFONHmpiFg,1565
|
806
851
|
sglang/srt/multimodal/processors/llava.py,sha256=-YtDc_7TsMWmwKkD4KJZW2Y0jPFlZtbQ38K_N24hk0w,8231
|
@@ -813,29 +858,35 @@ sglang/srt/multimodal/processors/qwen_audio.py,sha256=xkIFrHepF8Ok6MB-1OwVz1BmzP
|
|
813
858
|
sglang/srt/multimodal/processors/qwen_vl.py,sha256=tZOpz8dabyNvjS4hn0UxLf-EaEZH8kmHjyZaYRm9EZ8,10498
|
814
859
|
sglang/srt/multimodal/processors/step3_vl.py,sha256=9OI6UW9ybGbAnYN_S-5jh7TN8BGM_bQkvh1AHBJKzAQ,18350
|
815
860
|
sglang/srt/multimodal/processors/vila.py,sha256=vWgV1lTdjiFiTR8w-7fC66-L_tpOOD59c-c9NljGelE,2192
|
861
|
+
sglang/srt/parser/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
862
|
+
sglang/srt/parser/conversation.py,sha256=cmVT4SCqRYxprYvmftUC_z_TkhXCqYC9B2rVZsmQe30,38869
|
863
|
+
sglang/srt/parser/harmony_parser.py,sha256=YweG4azWm5jmzYGaAHEXSaORpgWctPpSGQk_jp5H-CE,23227
|
864
|
+
sglang/srt/parser/jinja_template_utils.py,sha256=XCuqi6iHQrtziUvhy22ePdh8WcS42O9sKxuXpM_bMXc,7836
|
865
|
+
sglang/srt/parser/reasoning_parser.py,sha256=3P5viZ4oCsz695rZULWnRKSYBJxouHjihdpZMBuY9yc,11159
|
816
866
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
817
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
867
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=0hPeAOJeJZdVets_Kseh2RZUtS4n96pMa4kJr227Ltk,14852
|
818
868
|
sglang/srt/sampling/sampling_params.py,sha256=HbVcCeSXgPW19MRB-v0FTG1D-zHDAY6-toxyndSl-zI,6462
|
819
869
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
820
870
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
821
871
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
822
|
-
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=
|
872
|
+
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=Romk41ahToaVlNMnnd1Enko7_kRA4KdMGO94qnEbDHA,6061
|
823
873
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
824
874
|
sglang/srt/speculative/build_eagle_tree.py,sha256=O9LJNaBflgJdWT94D-rGH1gJFJ18nst2oOD8HnA2mZ4,12859
|
825
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=
|
826
|
-
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=
|
875
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=4U4ubjqihqRAio5YzEksu56NXDRDQFVsriQ9sDWTexc,14167
|
876
|
+
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=FgKuBfDYYF5DnNTstRJ4t6lgrI-YuLTaTvCs7HH22qA,15818
|
827
877
|
sglang/srt/speculative/eagle_utils.py,sha256=H-2aqm3REztUXLnmhi31ck3TWPPMVKc2CUkWBPsFK44,47785
|
828
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
829
|
-
sglang/srt/speculative/spec_info.py,sha256=
|
830
|
-
sglang/srt/
|
878
|
+
sglang/srt/speculative/eagle_worker.py,sha256=bgkazRv585Ve4r89R9EJlZeN1WoWy_XbcgZL7QyGhgk,45205
|
879
|
+
sglang/srt/speculative/spec_info.py,sha256=f0d2-Zm8egnGBxqW4-OFOi9eaYk4KL4LZnc-e_c7dS4,877
|
880
|
+
sglang/srt/speculative/standalone_worker.py,sha256=jcM_-7DMtRUMC9R0YeD6815kaWuftkFe8LIo7ThLVCc,4069
|
881
|
+
sglang/srt/tokenizer/tiktoken_tokenizer.py,sha256=KJwr6Xlc7AdHegMTnAVKJlPpW59Z7AE27GTzFL78GwI,6222
|
831
882
|
sglang/srt/weight_sync/tensor_bucket.py,sha256=vp_LRrhULNnxiw9Tf56FcEckgUg07lifgv1lasG6y7o,3695
|
832
|
-
sglang/srt/weight_sync/utils.py,sha256=
|
883
|
+
sglang/srt/weight_sync/utils.py,sha256=WoZH_5qJTey-aV-qPgOgYoaGeAwrOy7Z8pQZREpgUaA,4149
|
833
884
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
834
885
|
sglang/test/doc_patch.py,sha256=P9PYjBIVlZHvP9M34qS-8m1scmDP27ciNJNvZOdrUKE,1614
|
835
|
-
sglang/test/few_shot_gsm8k.py,sha256=
|
886
|
+
sglang/test/few_shot_gsm8k.py,sha256=zalplyHOYCnIwAnSQg-xlZl-Q-wGuMfjLdl9EJnUN7U,4333
|
836
887
|
sglang/test/few_shot_gsm8k_engine.py,sha256=h88s3HzEStA1zjQkR-AgIEOQMwJMSnPHkX_wGBWXUYw,3907
|
837
888
|
sglang/test/run_eval.py,sha256=VnbcmUhceDUU3-nXlZ6uQMM3MEvnZh1gzP3LXxYkuxc,4251
|
838
|
-
sglang/test/runners.py,sha256=
|
889
|
+
sglang/test/runners.py,sha256=HenubP5mlRQ2i3G8pS9q4gdzYGC0cVSIbaAjKmmkPac,34099
|
839
890
|
sglang/test/send_one.py,sha256=XNZdfZs21tXDBwrDj2pq46WQd5smiKoYETY8U09c1Z8,5079
|
840
891
|
sglang/test/simple_eval_common.py,sha256=B60Yi3ox2Yubsq8M3BbApQTfmLhwQoL4ciS2ac12SM4,12702
|
841
892
|
sglang/test/simple_eval_gpqa.py,sha256=M6hpPs8l2Z4wUiyE7rCU1zyKoImXB4Z395Hgz43uvvQ,3293
|
@@ -848,23 +899,24 @@ sglang/test/test_block_fp8.py,sha256=mOM-eX9LisotPlMLSCvH4XwWMbvNpVOBtt7euXuVTDw
|
|
848
899
|
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7Xx0MjOoOBYL8J7ETvOVA,8180
|
849
900
|
sglang/test/test_block_fp8_ep.py,sha256=n4X6ZKwuUUbV5Ofjg64ptlaFGI1LbRXDfFiJW1ELHgY,10546
|
850
901
|
sglang/test/test_custom_ops.py,sha256=PenQ8zM1wj5xwiVEPVzD37pO-x90aOfFMpCRZenaKsY,5709
|
851
|
-
sglang/test/test_cutlass_moe.py,sha256=
|
852
|
-
sglang/test/test_cutlass_w4a8_moe.py,sha256=
|
902
|
+
sglang/test/test_cutlass_moe.py,sha256=WHCruIMzxzRzxQEeFEUtk0e0IefjiO0Kjfgnx42r0UI,10069
|
903
|
+
sglang/test/test_cutlass_w4a8_moe.py,sha256=Ku9VCXEMJ3BwXtvb1A3FzY-zek-S-A4thWyX6m-1v-A,9219
|
853
904
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
905
|
+
sglang/test/test_disaggregation_utils.py,sha256=S9GbriBYqbxpG-GZXs6wafeo4IFAFL7xAUHJSZ6RDpE,1962
|
854
906
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
855
907
|
sglang/test/test_fp4_moe.py,sha256=rJLkKW3glBMvI5Ed0LltOHi8zCReMa-WB50p5zGm6J4,10189
|
856
908
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
857
909
|
sglang/test/test_marlin_moe.py,sha256=TOuYlVMx2Lv_IN3AMWsg5aGaxQF472E1B9ev_vvfU2Q,7971
|
858
910
|
sglang/test/test_marlin_utils.py,sha256=kC7IzN364mJT9xw0nKUP1V1OK1hkw6fQTBvD4nRaOz4,5151
|
859
911
|
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
860
|
-
sglang/test/test_utils.py,sha256=
|
912
|
+
sglang/test/test_utils.py,sha256=kvG4B6KLtKirsUf09CI0uU3zAlX5_G9ND29YyMOfW78,42369
|
861
913
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
862
914
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
863
915
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
864
916
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
865
|
-
sglang/test/attention/test_trtllm_mla_backend.py,sha256=
|
866
|
-
sglang-0.5.
|
867
|
-
sglang-0.5.
|
868
|
-
sglang-0.5.
|
869
|
-
sglang-0.5.
|
870
|
-
sglang-0.5.
|
917
|
+
sglang/test/attention/test_trtllm_mla_backend.py,sha256=wp2_LSTwQ_vIdNPUCbEz7PA4doDU8sTWs6s6XVI0YnI,48874
|
918
|
+
sglang-0.5.2.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
919
|
+
sglang-0.5.2.dist-info/METADATA,sha256=gCmkuof6IzQx7RoawKqcZNLFMxpdGL0wdHDhU8T-s7k,28268
|
920
|
+
sglang-0.5.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
921
|
+
sglang-0.5.2.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
922
|
+
sglang-0.5.2.dist-info/RECORD,,
|