sglang 0.5.0rc2__py3-none-any.whl → 0.5.1__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 +0 -6
- sglang/bench_one_batch_server.py +7 -2
- sglang/bench_serving.py +3 -3
- sglang/eval/llama3_eval.py +0 -1
- sglang/srt/configs/model_config.py +24 -9
- sglang/srt/configs/update_config.py +40 -5
- sglang/srt/constrained/xgrammar_backend.py +23 -11
- sglang/srt/conversation.py +2 -15
- sglang/srt/disaggregation/ascend/conn.py +1 -3
- sglang/srt/disaggregation/base/conn.py +1 -0
- sglang/srt/disaggregation/decode.py +1 -1
- sglang/srt/disaggregation/launch_lb.py +7 -1
- sglang/srt/disaggregation/mini_lb.py +11 -5
- sglang/srt/disaggregation/mooncake/conn.py +141 -47
- sglang/srt/disaggregation/prefill.py +261 -5
- sglang/srt/disaggregation/utils.py +2 -1
- sglang/srt/distributed/device_communicators/custom_all_reduce.py +1 -1
- sglang/srt/distributed/device_communicators/pynccl.py +68 -18
- sglang/srt/distributed/device_communicators/pynccl_wrapper.py +52 -0
- sglang/srt/distributed/naive_distributed.py +112 -0
- sglang/srt/distributed/parallel_state.py +90 -4
- sglang/srt/entrypoints/context.py +20 -1
- sglang/srt/entrypoints/engine.py +27 -2
- sglang/srt/entrypoints/http_server.py +12 -0
- sglang/srt/entrypoints/openai/protocol.py +2 -2
- sglang/srt/entrypoints/openai/serving_chat.py +22 -6
- sglang/srt/entrypoints/openai/serving_completions.py +9 -1
- sglang/srt/entrypoints/openai/serving_responses.py +2 -2
- sglang/srt/eplb/expert_distribution.py +2 -3
- sglang/srt/function_call/deepseekv3_detector.py +1 -1
- sglang/srt/hf_transformers_utils.py +24 -0
- sglang/srt/host_shared_memory.py +83 -0
- sglang/srt/layers/attention/ascend_backend.py +132 -22
- sglang/srt/layers/attention/flashattention_backend.py +24 -17
- sglang/srt/layers/attention/flashinfer_backend.py +11 -3
- sglang/srt/layers/attention/flashinfer_mla_backend.py +226 -76
- sglang/srt/layers/attention/triton_backend.py +85 -46
- sglang/srt/layers/attention/triton_ops/decode_attention.py +33 -2
- sglang/srt/layers/attention/triton_ops/extend_attention.py +32 -2
- sglang/srt/layers/attention/trtllm_mha_backend.py +390 -30
- sglang/srt/layers/attention/trtllm_mla_backend.py +39 -16
- sglang/srt/layers/attention/utils.py +94 -15
- sglang/srt/layers/attention/vision.py +40 -13
- sglang/srt/layers/attention/vision_utils.py +65 -0
- sglang/srt/layers/communicator.py +51 -3
- sglang/srt/layers/dp_attention.py +23 -4
- sglang/srt/layers/elementwise.py +94 -0
- sglang/srt/layers/flashinfer_comm_fusion.py +29 -1
- sglang/srt/layers/layernorm.py +8 -1
- sglang/srt/layers/linear.py +24 -0
- sglang/srt/layers/logits_processor.py +5 -1
- sglang/srt/layers/moe/__init__.py +31 -0
- sglang/srt/layers/moe/ep_moe/layer.py +37 -33
- sglang/srt/layers/moe/fused_moe_native.py +14 -25
- 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 +146 -0
- 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 +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +146 -0
- 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 +146 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +69 -76
- sglang/srt/layers/moe/fused_moe_triton/layer.py +66 -123
- sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py +20 -18
- sglang/srt/layers/moe/moe_runner/__init__.py +3 -0
- sglang/srt/layers/moe/moe_runner/base.py +13 -0
- sglang/srt/layers/moe/rocm_moe_utils.py +141 -0
- sglang/srt/layers/moe/router.py +15 -9
- sglang/srt/layers/moe/token_dispatcher/__init__.py +6 -0
- sglang/srt/layers/moe/token_dispatcher/base_dispatcher.py +55 -14
- sglang/srt/layers/moe/token_dispatcher/deepep.py +11 -21
- sglang/srt/layers/moe/token_dispatcher/standard.py +1 -1
- sglang/srt/layers/moe/topk.py +167 -83
- sglang/srt/layers/moe/utils.py +159 -18
- sglang/srt/layers/quantization/__init__.py +13 -14
- sglang/srt/layers/quantization/awq.py +7 -7
- sglang/srt/layers/quantization/base_config.py +2 -6
- sglang/srt/layers/quantization/blockwise_int8.py +4 -12
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +72 -28
- sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py +2 -1
- sglang/srt/layers/quantization/fp8.py +127 -119
- sglang/srt/layers/quantization/fp8_kernel.py +195 -24
- sglang/srt/layers/quantization/fp8_utils.py +34 -9
- sglang/srt/layers/quantization/fpgemm_fp8.py +203 -0
- sglang/srt/layers/quantization/gptq.py +5 -4
- sglang/srt/layers/quantization/marlin_utils.py +11 -3
- sglang/srt/layers/quantization/marlin_utils_fp8.py +352 -0
- sglang/srt/layers/quantization/modelopt_quant.py +165 -68
- sglang/srt/layers/quantization/moe_wna16.py +10 -15
- sglang/srt/layers/quantization/mxfp4.py +206 -37
- sglang/srt/layers/quantization/quark/quark.py +390 -0
- sglang/srt/layers/quantization/quark/quark_moe.py +197 -0
- sglang/srt/layers/quantization/unquant.py +34 -70
- sglang/srt/layers/quantization/utils.py +25 -0
- sglang/srt/layers/quantization/w4afp8.py +7 -8
- sglang/srt/layers/quantization/w8a8_fp8.py +5 -13
- sglang/srt/layers/quantization/w8a8_int8.py +5 -13
- sglang/srt/layers/radix_attention.py +6 -0
- sglang/srt/layers/rotary_embedding.py +1 -0
- sglang/srt/lora/lora_manager.py +21 -22
- sglang/srt/lora/lora_registry.py +3 -3
- sglang/srt/lora/mem_pool.py +26 -24
- sglang/srt/lora/utils.py +10 -12
- sglang/srt/managers/cache_controller.py +76 -18
- sglang/srt/managers/detokenizer_manager.py +10 -2
- sglang/srt/managers/io_struct.py +9 -0
- sglang/srt/managers/mm_utils.py +1 -1
- sglang/srt/managers/schedule_batch.py +4 -9
- sglang/srt/managers/scheduler.py +25 -16
- sglang/srt/managers/session_controller.py +1 -1
- sglang/srt/managers/template_manager.py +7 -5
- sglang/srt/managers/tokenizer_manager.py +60 -21
- sglang/srt/managers/tp_worker.py +1 -0
- sglang/srt/managers/utils.py +59 -1
- sglang/srt/mem_cache/allocator.py +7 -5
- sglang/srt/mem_cache/allocator_ascend.py +0 -11
- sglang/srt/mem_cache/hicache_storage.py +14 -4
- sglang/srt/mem_cache/memory_pool.py +3 -3
- sglang/srt/mem_cache/memory_pool_host.py +35 -2
- sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py +56 -12
- sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py +8 -4
- sglang/srt/mem_cache/storage/nixl/hicache_nixl.py +153 -59
- sglang/srt/mem_cache/storage/nixl/nixl_utils.py +19 -53
- sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py +46 -7
- sglang/srt/model_executor/cuda_graph_runner.py +25 -12
- sglang/srt/model_executor/forward_batch_info.py +4 -1
- sglang/srt/model_executor/model_runner.py +43 -32
- sglang/srt/model_executor/npu_graph_runner.py +94 -0
- sglang/srt/model_loader/loader.py +24 -6
- sglang/srt/models/dbrx.py +12 -6
- sglang/srt/models/deepseek.py +2 -1
- sglang/srt/models/deepseek_nextn.py +3 -1
- sglang/srt/models/deepseek_v2.py +224 -223
- sglang/srt/models/ernie4.py +2 -2
- sglang/srt/models/glm4_moe.py +25 -63
- sglang/srt/models/glm4v.py +52 -1
- sglang/srt/models/glm4v_moe.py +8 -11
- sglang/srt/models/gpt_oss.py +34 -74
- sglang/srt/models/granitemoe.py +0 -1
- sglang/srt/models/grok.py +376 -48
- sglang/srt/models/interns1.py +12 -47
- sglang/srt/models/internvl.py +6 -51
- sglang/srt/models/llama4.py +0 -2
- sglang/srt/models/minicpm3.py +0 -1
- sglang/srt/models/mixtral.py +0 -2
- sglang/srt/models/nemotron_nas.py +435 -0
- sglang/srt/models/olmoe.py +0 -1
- sglang/srt/models/phi4mm.py +3 -21
- sglang/srt/models/qwen2_5_vl.py +2 -0
- sglang/srt/models/qwen2_moe.py +3 -18
- sglang/srt/models/qwen3.py +2 -2
- sglang/srt/models/qwen3_classification.py +7 -1
- sglang/srt/models/qwen3_moe.py +9 -38
- sglang/srt/models/step3_vl.py +2 -1
- sglang/srt/models/xverse_moe.py +11 -5
- sglang/srt/multimodal/processors/base_processor.py +3 -3
- sglang/srt/multimodal/processors/internvl.py +7 -2
- sglang/srt/multimodal/processors/llava.py +11 -7
- sglang/srt/offloader.py +433 -0
- sglang/srt/operations.py +6 -1
- sglang/srt/reasoning_parser.py +4 -3
- sglang/srt/server_args.py +237 -104
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +1 -0
- sglang/srt/speculative/eagle_utils.py +36 -13
- sglang/srt/speculative/eagle_worker.py +56 -3
- sglang/srt/tokenizer/tiktoken_tokenizer.py +161 -0
- sglang/srt/two_batch_overlap.py +16 -11
- sglang/srt/utils.py +68 -70
- sglang/test/runners.py +8 -5
- sglang/test/test_block_fp8.py +5 -6
- sglang/test/test_block_fp8_ep.py +13 -19
- sglang/test/test_cutlass_moe.py +4 -6
- sglang/test/test_cutlass_w4a8_moe.py +4 -3
- sglang/test/test_fp4_moe.py +4 -3
- sglang/test/test_utils.py +7 -0
- sglang/utils.py +0 -1
- sglang/version.py +1 -1
- {sglang-0.5.0rc2.dist-info → sglang-0.5.1.dist-info}/METADATA +7 -7
- {sglang-0.5.0rc2.dist-info → sglang-0.5.1.dist-info}/RECORD +179 -161
- sglang/srt/layers/quantization/fp4.py +0 -557
- {sglang-0.5.0rc2.dist-info → sglang-0.5.1.dist-info}/WHEEL +0 -0
- {sglang-0.5.0rc2.dist-info → sglang-0.5.1.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.5.0rc2.dist-info → sglang-0.5.1.dist-info}/top_level.txt +0 -0
@@ -1,16 +1,16 @@
|
|
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=8Aic1FibvTpRtxtZx0fK97v8n7MQYLzg9Hg4t64iorQ,23041
|
4
|
+
sglang/bench_one_batch_server.py,sha256=c9n1gsGI435eQz9dOqKAP11t32kmkCLJ_EW4gWtPSeU,14340
|
5
|
+
sglang/bench_serving.py,sha256=xR1blR5t0t6YDEIOXvxjhrL7XkptBBV4VeQGZIORvLQ,71791
|
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=tEHzHerXC-ymk4OrkoUcMbgcGHmb8VESthsNSP2Yx9w,4417
|
11
|
-
sglang/utils.py,sha256=
|
12
|
-
sglang/version.py,sha256=
|
13
|
-
sglang/eval/llama3_eval.py,sha256=
|
11
|
+
sglang/utils.py,sha256=dC2PNkKYTgDHsNrWdZJ74GvaXGSHCeIk_aZ-TA89OhY,16380
|
12
|
+
sglang/version.py,sha256=eZ1bOun1DDVV0YLOBW4wj2FP1ajReLjbIrGmzN7ASBw,22
|
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
|
@@ -30,20 +30,22 @@ sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
|
30
30
|
sglang/srt/bench_utils.py,sha256=zNTsTBUta27XxojgvR5p5X9M0v1MFzZ7dcX9TMq4NvQ,4348
|
31
31
|
sglang/srt/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
32
32
|
sglang/srt/constants.py,sha256=0i-tEwG2BSYNDy96MxnGHV5HnBELkYcnsVGsE-R18o0,93
|
33
|
-
sglang/srt/conversation.py,sha256=
|
33
|
+
sglang/srt/conversation.py,sha256=7WkS3GZjGVt82hUglXdYBUdf13vk6U3-mN6KAGPMrCw,37822
|
34
34
|
sglang/srt/custom_op.py,sha256=7OPQAZe3PqDXk-xM0Wxl7pm9cazilNJfkNiYIWztWgI,3198
|
35
|
-
sglang/srt/hf_transformers_utils.py,sha256=
|
35
|
+
sglang/srt/hf_transformers_utils.py,sha256=WgpIr56YuKG8Hmp_vrZBfePYWMzDPVhH8k0p4DLk5sA,14877
|
36
|
+
sglang/srt/host_shared_memory.py,sha256=00TgVm3PNCl4rTPJZChG5uu4I5hd_Xf587r39tibmIg,2274
|
36
37
|
sglang/srt/jinja_template_utils.py,sha256=XCuqi6iHQrtziUvhy22ePdh8WcS42O9sKxuXpM_bMXc,7836
|
37
38
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
38
|
-
sglang/srt/
|
39
|
+
sglang/srt/offloader.py,sha256=Bgob16HwmiQXt5yV0okin-UgcdMLHpEDXI0OtHfi6vI,14138
|
40
|
+
sglang/srt/operations.py,sha256=za_h1_kcR1Te6-i_r0i_zAeumbmIRhLK2pS31sukkrw,6089
|
39
41
|
sglang/srt/operations_strategy.py,sha256=-w6GI2VgSGvORy3pUWRAJo6244ykSW1ZBV1Dx0fZlHA,7138
|
40
42
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
41
43
|
sglang/srt/poll_based_barrier.py,sha256=9vjn32ROlSueEk7EuZjWKUrrL7XVR9KJsSVliGTYB_4,937
|
42
|
-
sglang/srt/reasoning_parser.py,sha256=
|
43
|
-
sglang/srt/server_args.py,sha256
|
44
|
+
sglang/srt/reasoning_parser.py,sha256=er9PSDKroGhXG52k0Kz9Aw5o_7rpN1LXVp5mmZgtzqY,22948
|
45
|
+
sglang/srt/server_args.py,sha256=-HMb560gDy7a3_HDh2St8nvkLv00dyKCX2s22ufkNew,102455
|
44
46
|
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
45
|
-
sglang/srt/two_batch_overlap.py,sha256=
|
46
|
-
sglang/srt/utils.py,sha256=
|
47
|
+
sglang/srt/two_batch_overlap.py,sha256=UykF5nC2rja3Hvmu0D9glqKdVRIEhQGPV84Jm7veopQ,34150
|
48
|
+
sglang/srt/utils.py,sha256=ts1LtMbDygqKdlDunDmMn7wIk_6_X3WTZ0U_tzs4eXQ,93412
|
47
49
|
sglang/srt/warmup.py,sha256=zldxhMlXpclRAJXmfBjJNUJd1eDizVdysibBvQyTVuA,1782
|
48
50
|
sglang/srt/configs/__init__.py,sha256=gas3cKYVgZp7qF4m8FejX4EUUmdQd_w5WDTm7fo7yM0,743
|
49
51
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
@@ -56,9 +58,9 @@ sglang/srt/configs/janus_pro.py,sha256=yI2c_aWBIKiTcK6RZxK6hq8CIxyYRH_NN8uaSNKsr
|
|
56
58
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
57
59
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
58
60
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
59
|
-
sglang/srt/configs/model_config.py,sha256=
|
61
|
+
sglang/srt/configs/model_config.py,sha256=TbXN5Vne86gmaIq5E5In30nVvcuPms8mCi7Cn2b6sQw,30967
|
60
62
|
sglang/srt/configs/step3_vl.py,sha256=_Otgnym57DVgB_kZ__8c1_Ys5gSalA_K0ZuVjcG51T0,4845
|
61
|
-
sglang/srt/configs/update_config.py,sha256=
|
63
|
+
sglang/srt/configs/update_config.py,sha256=GEf-XhL8JPrbX9-Hz8V7S3M6YTg76DVdIhc_4YdMDtc,6291
|
62
64
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
63
65
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
64
66
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -73,72 +75,73 @@ sglang/srt/constrained/llguidance_backend.py,sha256=Au8G8x4EB39w7k9-GFLP2hOPETye
|
|
73
75
|
sglang/srt/constrained/outlines_backend.py,sha256=4Er45scnqHuJQ14kggsVX3RoHlaUD9t0ALIoWDQEmFg,6913
|
74
76
|
sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
|
75
77
|
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
76
|
-
sglang/srt/constrained/xgrammar_backend.py,sha256=
|
78
|
+
sglang/srt/constrained/xgrammar_backend.py,sha256=7mwm78Fx21psAseBrQlzVJuPg2YY5aw7GI6J6qLxGNQ,8608
|
77
79
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
78
80
|
sglang/srt/debug_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
79
81
|
sglang/srt/debug_utils/dump_comparator.py,sha256=8ZPwP0zojfRHvPiSKgpESYFcC3tR-sBjIej5SotOmpg,3947
|
80
82
|
sglang/srt/debug_utils/dumper.py,sha256=eyrg5lmwyYF88kn8b06kpu1__aGnWb6CLM8fxywtooI,3158
|
81
83
|
sglang/srt/debug_utils/text_comparator.py,sha256=pg58q3fzsnd3rJKRgZTdcOviOtAv8pSYZdwf-TLffMM,5522
|
82
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
84
|
+
sglang/srt/disaggregation/decode.py,sha256=sdV8sGhwk4sX-V4p3xjxkqql0YZjsgnPOf6dG5UJSB4,34325
|
83
85
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=Iu7ehHGAfYIVATtClwX6y-6zxWs-JyDlMotYo_5yuUc,6598
|
84
86
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
85
|
-
sglang/srt/disaggregation/launch_lb.py,sha256=
|
86
|
-
sglang/srt/disaggregation/mini_lb.py,sha256=
|
87
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
88
|
-
sglang/srt/disaggregation/utils.py,sha256=
|
87
|
+
sglang/srt/disaggregation/launch_lb.py,sha256=pmHwo1GWbpHZn4IDKnOEHYVcfdKpsYuTHUMowNo3TrE,3891
|
88
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=4l3W2COZuX8DbLg8AQvAhv5EncH9FkEv2HF5fhn3GQM,14630
|
89
|
+
sglang/srt/disaggregation/prefill.py,sha256=wA-sXQG0t3hqzXDZcp5H6wI5F6qkZ-3CyzIX5Nc5v_w,36019
|
90
|
+
sglang/srt/disaggregation/utils.py,sha256=evdv4AkQxJzTqdO0jrdAr7vHUbBSCEXMzNREh0FoRLc,12294
|
89
91
|
sglang/srt/disaggregation/ascend/__init__.py,sha256=-lxnica6fZYmYNpKwmE8yESUpQ5Sxf2DiZoBHzboKc8,146
|
90
|
-
sglang/srt/disaggregation/ascend/conn.py,sha256=
|
92
|
+
sglang/srt/disaggregation/ascend/conn.py,sha256=oBhEQ83SbIlYc7QSG6Cqk48QqdYSlxcSMWbc-2KXlXM,1191
|
91
93
|
sglang/srt/disaggregation/ascend/transfer_engine.py,sha256=_4PszsQL6wICdg5cqpR2N9TbZpUY6bBX8tgE3xeaYfc,2137
|
92
94
|
sglang/srt/disaggregation/base/__init__.py,sha256=4VwUv0aWxwmVL1049XK82aLTNxmt0WY5RPy9li-wyVk,160
|
93
|
-
sglang/srt/disaggregation/base/conn.py,sha256=
|
95
|
+
sglang/srt/disaggregation/base/conn.py,sha256=xQ-UB_brdn9vHr-NSbzuR6BysDPGh0Pt9h836iUgbX8,2901
|
94
96
|
sglang/srt/disaggregation/common/__init__.py,sha256=7yl-EGLMVKRpBUaGF_7lwAsw2J_mqpRZV0238VGxD9o,126
|
95
97
|
sglang/srt/disaggregation/common/conn.py,sha256=3YJVviObY3fkSfQbVxE5lgcqMmqM5nDjWfEjS5-SW6I,17054
|
96
98
|
sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeKVPMWPcB5ywbE,1194
|
97
99
|
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
98
100
|
sglang/srt/disaggregation/fake/conn.py,sha256=oD1DArn1yDFZCu-X6p93uSLlAXEkt9lYxERICMznxGw,2286
|
99
101
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
100
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
102
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=7rXwVA2s12bl-_ccCVdVuJ8weu2dLGPKSl_IS9iHfPw,71343
|
101
103
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=O-XRmQ3QwD6RuiyRgw4ZohSrFkuPdppV_eDBMUXn0jk,5884
|
102
104
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
103
105
|
sglang/srt/disaggregation/nixl/conn.py,sha256=eSof87fG21Dd4COszfnbeXIxne3TWvw0mSvCOkjsBZc,20323
|
104
106
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
105
107
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
106
|
-
sglang/srt/distributed/
|
108
|
+
sglang/srt/distributed/naive_distributed.py,sha256=5Kcfapzz61G3TtScTZrHoWa4bf6Vr27GlMcBAGMz7tQ,3260
|
109
|
+
sglang/srt/distributed/parallel_state.py,sha256=ic89h9Ze1yKMnY5s-mpO23LP-DH0zLXmvxDkRWgxILg,65200
|
107
110
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
108
111
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
109
|
-
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=
|
112
|
+
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=Q1kkKPKFPV0QMmKLyjOBlOnX8-Pr4UeGBZYkG6j0gc0,16570
|
110
113
|
sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py,sha256=Fx9D70NO2dplyuqOxTasMwkzONN3wfC4WOny3tWSbPA,14159
|
111
114
|
sglang/srt/distributed/device_communicators/hpu_communicator.py,sha256=gPjEH1-izoby5uDrfUlzNf21luPT0Ow7pJjhCRKnHy8,1728
|
112
115
|
sglang/srt/distributed/device_communicators/npu_communicator.py,sha256=bRXN1Md_4SHQGzQYZa2GrHv2zbIU5vSpkueHiAZL1xQ,1345
|
113
116
|
sglang/srt/distributed/device_communicators/pymscclpp.py,sha256=8Pgehd02v-BpHixTTB4OB9ZlxA7fyXiPF4Xp9F_heyU,10890
|
114
|
-
sglang/srt/distributed/device_communicators/pynccl.py,sha256=
|
117
|
+
sglang/srt/distributed/device_communicators/pynccl.py,sha256=7aE-pKMyJfawGo7Vzymb6Nlz3ux2G_dPflYPK2kzpaQ,12208
|
115
118
|
sglang/srt/distributed/device_communicators/pynccl_allocator.py,sha256=zAxWwI73ZNsF_c4PZUnRMzwzSD88v26w8komzZ4Uatc,4771
|
116
|
-
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=
|
119
|
+
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=BLGEl90GZSl3K-04x7eCTaVmpZBXpcb7uJakAseteFU,18539
|
117
120
|
sglang/srt/distributed/device_communicators/quick_all_reduce.py,sha256=4j1_E4azoxfd8wxtfFmt9rvbQncl8ny6wmTMl6gAkp0,9932
|
118
121
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=IrSrnpZnii0EJTS1CYRwEwE7gyHxJBVgI2QuJS3AKW0,20906
|
119
122
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
120
123
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
121
|
-
sglang/srt/entrypoints/context.py,sha256=
|
122
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
124
|
+
sglang/srt/entrypoints/context.py,sha256=aD-94xkD0komuGO5gtYUoJKCHdc4hAipMxQt04yVRGA,8030
|
125
|
+
sglang/srt/entrypoints/engine.py,sha256=2x5OhR3CEOrPwMCKIkRxXk0LLGZI4e8vamjGkHQ5g3s,33151
|
123
126
|
sglang/srt/entrypoints/harmony_utils.py,sha256=01T-A5GBUm2b306PcxNEg2rfx4cykBcqNYrzcXTWBlc,13590
|
124
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
127
|
+
sglang/srt/entrypoints/http_server.py,sha256=B_nV6dqQWOHj2t_r0_rip30AMfJ8ZTgnIUJLeVt3qQw,44249
|
125
128
|
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
126
129
|
sglang/srt/entrypoints/tool.py,sha256=6fyXArrLqDsZO3rTtPfZ_6ngYLfTMRyyTSvESqos5tA,2678
|
127
130
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
128
|
-
sglang/srt/entrypoints/openai/protocol.py,sha256=
|
131
|
+
sglang/srt/entrypoints/openai/protocol.py,sha256=S_uMVVg8LwxN__O6corf60VqayNQMAGM_BxxU916RGE,26499
|
129
132
|
sglang/srt/entrypoints/openai/serving_base.py,sha256=epD6J7K72p6TP8o2dGYf-a76nXeF80vFhPRpWts6684,5445
|
130
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
131
|
-
sglang/srt/entrypoints/openai/serving_completions.py,sha256=
|
133
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=uI9NjmB-Rqnvsm70i6D0zZaJnacxkOuMYnxuBWMKPdc,41008
|
134
|
+
sglang/srt/entrypoints/openai/serving_completions.py,sha256=ByM6SJEDA-y0VV2MdkuLMdlb4mDRtD81tQtyMfB0SdE,17088
|
132
135
|
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=hqPt2ELpT1yQ8sBXo801aLJ3sExoPXs_K5ZQtC2vpAs,6274
|
133
136
|
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=8n6y5kC6UhRpWrDtzH0eIp0dznW12FT60MLCR4bvD2U,3333
|
134
|
-
sglang/srt/entrypoints/openai/serving_responses.py,sha256=
|
137
|
+
sglang/srt/entrypoints/openai/serving_responses.py,sha256=aTdC98ZvqAjmGn6VntVw_c8OwtVYZnsewDjQGtKZ8q0,53398
|
135
138
|
sglang/srt/entrypoints/openai/serving_score.py,sha256=ebAts-m6Pq-LTgFKwggkywBUrAgUSppHHVEzgwYHUzo,1955
|
136
139
|
sglang/srt/entrypoints/openai/tool_server.py,sha256=rRNGELPV5RHONp55MYkO4_b0NPsPffJnWg-gMYwDSTc,5659
|
137
140
|
sglang/srt/entrypoints/openai/usage_processor.py,sha256=9LTB5rqdRuMKyZrIXiUBuF_WKaSg9X45YdzERDxbtCY,2746
|
138
141
|
sglang/srt/entrypoints/openai/utils.py,sha256=DT9quW0F1DX1P9NAuMxpERgXcNYKKtm7rd7J1m7EaDQ,2112
|
139
142
|
sglang/srt/eplb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
140
143
|
sglang/srt/eplb/eplb_manager.py,sha256=Wt7w4L5g1BSsXx1mqoGo8WjkB55f4nGB4KqC3y_ijl8,3394
|
141
|
-
sglang/srt/eplb/expert_distribution.py,sha256=
|
144
|
+
sglang/srt/eplb/expert_distribution.py,sha256=HSv7kA8qeq25NJW0BcSRTNWQHF-YQsS82XhQMEqw7f8,31665
|
142
145
|
sglang/srt/eplb/expert_location.py,sha256=SIinJLiDhS4mctTiMdIQzQZFchwrrvES0ufEVJ4OGeg,17076
|
143
146
|
sglang/srt/eplb/expert_location_dispatch.py,sha256=vA0o-7bXf847BQAVCqElWKEpofZLAIsir_d0pew2KNQ,4178
|
144
147
|
sglang/srt/eplb/expert_location_updater.py,sha256=eMtJVMCRklfvKPbFiDKy85f5J9s_krJbpRCSArYZjVs,21157
|
@@ -149,7 +152,7 @@ sglang/srt/eplb/eplb_simulator/__init__.py,sha256=HIZaXqsvsOCMMJ81dSs1afSGZ5G6Oi
|
|
149
152
|
sglang/srt/eplb/eplb_simulator/reader.py,sha256=OlsWqsuXqVQY7PfvvrP-vsl2Ww2Kg4vD_K9BltM_QHo,1828
|
150
153
|
sglang/srt/function_call/base_format_detector.py,sha256=FKBzsGFHfNl3Wvccsdvv9ftjbCZIyyjOLj2kHgKvX9g,15901
|
151
154
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
152
|
-
sglang/srt/function_call/deepseekv3_detector.py,sha256=
|
155
|
+
sglang/srt/function_call/deepseekv3_detector.py,sha256=DhO3tUX1nvFlfRkHJ1Vm_7OMXFFTvWBA9u9SZKFAwuQ,9710
|
153
156
|
sglang/srt/function_call/ebnf_composer.py,sha256=f5Lqn3mtTtJ7LCJXAurVw2k4Zp5LgbWywQv7GsxSoPw,15000
|
154
157
|
sglang/srt/function_call/function_call_parser.py,sha256=YHt-5qIeFwueOQCiXzfKKwDXXkQ7AaNYvJlmNhMSt34,8211
|
155
158
|
sglang/srt/function_call/glm4_moe_detector.py,sha256=FS4Jhyt8_2xTTytNsQhzlNds2VQO_JIp3tKyCf7PtF0,6939
|
@@ -164,66 +167,69 @@ sglang/srt/function_call/step3_detector.py,sha256=SAibrispu0peDQzqOG2-V93KGHtV6U
|
|
164
167
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
165
168
|
sglang/srt/layers/activation.py,sha256=uhfhh10N5iLoLEBCvFPRjCfDxu5jXe1ehHJb3ISIjig,7840
|
166
169
|
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
167
|
-
sglang/srt/layers/communicator.py,sha256=
|
168
|
-
sglang/srt/layers/dp_attention.py,sha256=
|
169
|
-
sglang/srt/layers/elementwise.py,sha256=
|
170
|
-
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=
|
171
|
-
sglang/srt/layers/layernorm.py,sha256=
|
172
|
-
sglang/srt/layers/linear.py,sha256=
|
173
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
170
|
+
sglang/srt/layers/communicator.py,sha256=FyumhAAE0qJBk9v7B7ad_dzmSuM3KCk-dEAz1lWBj78,22660
|
171
|
+
sglang/srt/layers/dp_attention.py,sha256=35GQIpO8HpF9mtLQSJe2RW2a5rblTLvzAbr1CL0PbSg,15286
|
172
|
+
sglang/srt/layers/elementwise.py,sha256=PjYv7Sk-zKbG9WiGlYDKsxvNrnxT2N1Q8bA2BWvA1Uo,18771
|
173
|
+
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=hnVVS_VsWukTYhREubWs2KcJ1GjVMEI9ECqxqOMXZv8,6729
|
174
|
+
sglang/srt/layers/layernorm.py,sha256=3qanS30lgBGO8tiR5XaIW3ejJzB-8oYAD420Zjql2sw,9803
|
175
|
+
sglang/srt/layers/linear.py,sha256=f5BZqcbM-6qILXn9nDN2_Vd1Oy8THk0-5z1iw40jRxs,53397
|
176
|
+
sglang/srt/layers/logits_processor.py,sha256=jFWv46U6EkH7HLAlpGeC80iump5Kv2QZhHdj35RlQhc,26865
|
174
177
|
sglang/srt/layers/multimodal.py,sha256=vNswe0J0maeBiN8ehlmxfs-YYlrmMllYl6Nc_Y57Neg,5114
|
175
178
|
sglang/srt/layers/parameter.py,sha256=jCg0G-12GZqTa9gGOqEtVCsnnuBGnYg0VmF6pc6oCFg,17455
|
176
179
|
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
177
|
-
sglang/srt/layers/radix_attention.py,sha256=
|
178
|
-
sglang/srt/layers/rotary_embedding.py,sha256=
|
180
|
+
sglang/srt/layers/radix_attention.py,sha256=MpugwaqiY2zPTeg7FVW41OljljCXmYVvHZ2MvneF6PI,3745
|
181
|
+
sglang/srt/layers/rotary_embedding.py,sha256=MZ-P1wcVSr2YA0Iz-4qKIyL8G5p_-nVJU2EA5MVISgM,73102
|
179
182
|
sglang/srt/layers/sampler.py,sha256=cgtAtsxcllqhlrxk5ktiBEAeeVLZb-5wWb9NlGzkNYg,11199
|
180
183
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
181
184
|
sglang/srt/layers/utils.py,sha256=NEWsf7OlUgcX42WHXxANduDL0ByBm3beirCp8gvHDRs,1437
|
182
185
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=x0421kNUgnAb5LnkJR6O67vGZ0ikSD-ThluV3QGsZ_8,22673
|
183
186
|
sglang/srt/layers/attention/aiter_backend.py,sha256=XfZKrPFL1feerRMRL4jFoBGtbtoOD9gzKFCx8BomfJ4,43146
|
184
|
-
sglang/srt/layers/attention/ascend_backend.py,sha256=
|
187
|
+
sglang/srt/layers/attention/ascend_backend.py,sha256=ySS1XX5_tnBOG9uBrQRzNmWD1fuGkjJjnwtOjimXv6A,12779
|
185
188
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=_vM05ddWy6SaoqWYPR8w5lflSE4MhcVFR271Q9EKK8E,3600
|
186
189
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=PB5BjbJHhmTg_t0kXfarTI6C3pPvKhBAqvCSGGajou0,9846
|
187
190
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
188
191
|
sglang/srt/layers/attention/dual_chunk_flashattention_backend.py,sha256=hCATQEhBATZpPhBMF-cCM9r6nxXA0dr3jOT_hTFS_T0,68656
|
189
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
190
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
191
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
192
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=bB4lW2TqTr-j0TOk1nxOnCytRVtAksRECxqIRKx-VKQ,94851
|
193
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=J5Q5PeMyMo0NZa2BLgVWJZHST4UQCrifP6Rrv7iXlXc,54215
|
194
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=5dFkb7oD62MITS0V4Bc8b-NfFIJR3Lx3EroDTaiLm-Y,40985
|
192
195
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=5iSic5ho-lkXNas9mR3uLbXbEl-do31gc8gjR7-a79k,20711
|
193
196
|
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=dwbxscTGMOnwfxxPpmGdbSiQ0kQRHnH0pdpKHA-_vqc,3181
|
194
197
|
sglang/srt/layers/attention/intel_amx_backend.py,sha256=hH9lxXs_o66_IVs58oPhRCOXGUrHbXSz82FKtHr9GO8,4092
|
195
198
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
196
199
|
sglang/srt/layers/attention/tbo_backend.py,sha256=CBnSDUmDvT-Tbhi9NHNo1LLkgUAcIsWMJgKa-sAIKW8,9318
|
197
200
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=RsI4lYiQJAj-Xy0vKkzbyKOWHAVPOD9b0n0dEehwlos,9496
|
198
|
-
sglang/srt/layers/attention/triton_backend.py,sha256=
|
199
|
-
sglang/srt/layers/attention/trtllm_mha_backend.py,sha256=
|
200
|
-
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=
|
201
|
-
sglang/srt/layers/attention/utils.py,sha256=
|
202
|
-
sglang/srt/layers/attention/vision.py,sha256=
|
201
|
+
sglang/srt/layers/attention/triton_backend.py,sha256=fvcJLaJaM8JE9Q9Nkmn0dzdYnnYlwELCoxQGMoqS9Gk,41858
|
202
|
+
sglang/srt/layers/attention/trtllm_mha_backend.py,sha256=8MxCAzqsNuvO3mhFqTMXCJ0Tt0_82kFbBHie6m0ieDA,27588
|
203
|
+
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=pkXARtA9ISC3RL82mqjY7vzfsK-u1rvMRBcOn2n0J_o,19101
|
204
|
+
sglang/srt/layers/attention/utils.py,sha256=lIlHKwSYcS6R3RVWuoLj-5RnJAMMtmX9LxLAE-IgZKs,7025
|
205
|
+
sglang/srt/layers/attention/vision.py,sha256=PZUJuswPWvJ34NTtxJkcXnusojDv0pO0UhrsjL4SWYU,20268
|
206
|
+
sglang/srt/layers/attention/vision_utils.py,sha256=6hPPAt8p3SOm7tgHNUesnMLxvQiKbaOM5EK6K-ig5dI,2771
|
203
207
|
sglang/srt/layers/attention/wave_backend.py,sha256=_rjyALSl5huNtIGSe6OJlBrC04LhwBBu62bgjlkavkw,23010
|
204
|
-
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=
|
208
|
+
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=JnOtqtPXEgn_T0R4gGCROx1szlAhu_G_ODNKCazz0lE,20554
|
205
209
|
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
206
|
-
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=
|
210
|
+
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=eYg4xQoH5gBkM7bjzpBIpTdcelvUK3BujJ-8eXRCm70,17108
|
207
211
|
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
208
212
|
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
209
213
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
210
214
|
sglang/srt/layers/attention/wave_ops/decode_attention.py,sha256=C-W1hvswZ7ggDKp4lSRE7C_sjVxuuhvk7nTqF96aam0,4813
|
211
215
|
sglang/srt/layers/attention/wave_ops/extend_attention.py,sha256=aPNVsrhJD3OW7YF3jRm59IIawgA-bv_6GT91UPf5x5Y,3957
|
212
216
|
sglang/srt/layers/attention/wave_ops/prefill_attention.py,sha256=viTUit0rxjVV5UahuwmVAhmL66YRFJD4g1YhH_oRBu8,2344
|
217
|
+
sglang/srt/layers/moe/__init__.py,sha256=63TxUpSiUpVg1SDY1zdlTg3WFJzAc7WSndOViOmUv4E,835
|
213
218
|
sglang/srt/layers/moe/cutlass_moe.py,sha256=8WWLlEQF5pQHXGsFmmyLCNBo4i1kfI8a_CKg8ruztMQ,14800
|
214
219
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
215
220
|
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=rWyHMg0kYZhIdLWTJeC7pqRG9ywfeKqi47-OekNeF4Y,7306
|
216
|
-
sglang/srt/layers/moe/fused_moe_native.py,sha256=
|
217
|
-
sglang/srt/layers/moe/
|
218
|
-
sglang/srt/layers/moe/
|
219
|
-
sglang/srt/layers/moe/
|
221
|
+
sglang/srt/layers/moe/fused_moe_native.py,sha256=8SAToE4B-22H5JsENZgJ1Io6QfE5-D9ItWLtbGksFQQ,3372
|
222
|
+
sglang/srt/layers/moe/rocm_moe_utils.py,sha256=07Z99bTV3B-b2Cbm-odhGpx2twxtnVpYvaDMBE1K3LM,4555
|
223
|
+
sglang/srt/layers/moe/router.py,sha256=eUNu_Uz5VB2FOZzZyYuZo5pokCVBS17_fcjHQbmvDSE,12181
|
224
|
+
sglang/srt/layers/moe/topk.py,sha256=rD7bO7--LPT6NvQXksBwG8tAkCqJoaxzF5L03mvbXf0,30378
|
225
|
+
sglang/srt/layers/moe/utils.py,sha256=omh9E6sF-KtrELEsE9y01Ash7FfQlstyE-97UtpH8qk,5998
|
220
226
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
221
227
|
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=7MieYfBctQjqfBoKun_QUyfloIrrgt5tjzmMkMoY5Ys,44107
|
222
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
228
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=tJwbzSKT0qMRF2E4BDwyzFhUCBd1-KxInJxqmgrP-y8,28191
|
223
229
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=4NXZHbCw-G-uSnNUj4up0yh3xBDPnT-x0pdoIr0lku8,831
|
224
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
225
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
226
|
-
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=
|
230
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=JKp89Cdl8a85tKzmJa4ah5VtxZzRNBSbY4cnsAtnvio,60803
|
231
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=jub7moptP9UjyRYJ2gPvY8HEnE41d_oFbZgjVvNsJxQ,39409
|
232
|
+
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk0nPWQelgvi1rV9Z72FetRo6p7E3rsYs,10986
|
227
233
|
"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
|
228
234
|
"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
|
229
235
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ouRyZ5PEMPP2njPftCNhs-1g1y6wueWLmhI7G1SjV1k,4131
|
@@ -407,41 +413,48 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=fC9PGO2Z3XAQ
|
|
407
413
|
"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
|
408
414
|
"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
|
409
415
|
"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
|
+
"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
|
410
417
|
"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
|
418
|
+
"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
|
+
"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
|
+
"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
|
411
421
|
"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
|
412
|
-
sglang/srt/layers/moe/
|
413
|
-
sglang/srt/layers/moe/
|
414
|
-
sglang/srt/layers/moe/token_dispatcher/
|
415
|
-
sglang/srt/layers/moe/token_dispatcher/
|
416
|
-
sglang/srt/layers/
|
417
|
-
sglang/srt/layers/
|
422
|
+
sglang/srt/layers/moe/moe_runner/__init__.py,sha256=piJQmSz7BOBaxVd0gGMgRLzaD21r7PH1NEDOK5hktYk,97
|
423
|
+
sglang/srt/layers/moe/moe_runner/base.py,sha256=L7ZNcq6fQxMXQZypcxWKIe1j9ajoOKCsFRrF-UlHVaA,364
|
424
|
+
sglang/srt/layers/moe/token_dispatcher/__init__.py,sha256=M3Lx6ChYbDSS0PgeCrBfhFq1cf8tGBKrEXttoGCNA7s,739
|
425
|
+
sglang/srt/layers/moe/token_dispatcher/base_dispatcher.py,sha256=cr3TwI-UvLVfAdcFh0M4dtT4fdpOaUpznzDXoaLQlcw,2539
|
426
|
+
sglang/srt/layers/moe/token_dispatcher/deepep.py,sha256=UvTiTdr4d0GDBZWBmhHDJr5U3pETOCbNlwWIE2C2D7I,23597
|
427
|
+
sglang/srt/layers/moe/token_dispatcher/standard.py,sha256=J3gwLb7qOpaJeXMCLRlLx9FM71ejzwtlJK9mFSxMznM,430
|
428
|
+
sglang/srt/layers/quantization/__init__.py,sha256=GmJvVSlkJXf2AmTfWBN6EBrOhhYlxPYNE_eAEXMZfjs,7813
|
429
|
+
sglang/srt/layers/quantization/awq.py,sha256=-W4c4c5Df0h7d7mQKQFSJ9ZAxCtyWiOxpu55BSHFPwc,26588
|
418
430
|
sglang/srt/layers/quantization/awq_triton.py,sha256=4XwJbRNlFmlvjbMGtWF1Wvk26Kf96162vNEmuI5Kars,11737
|
419
|
-
sglang/srt/layers/quantization/base_config.py,sha256=
|
420
|
-
sglang/srt/layers/quantization/blockwise_int8.py,sha256=
|
421
|
-
sglang/srt/layers/quantization/
|
422
|
-
sglang/srt/layers/quantization/
|
423
|
-
sglang/srt/layers/quantization/
|
424
|
-
sglang/srt/layers/quantization/
|
425
|
-
sglang/srt/layers/quantization/gptq.py,sha256=
|
431
|
+
sglang/srt/layers/quantization/base_config.py,sha256=taPmvTT2ZMzXShSHoAAYEAjF6_bvIcUY9Oa_ED_SpkY,7066
|
432
|
+
sglang/srt/layers/quantization/blockwise_int8.py,sha256=juOCfNFreRrSNwT3IWwj1f7AzlGDsR7WVl_DOCUznvU,13584
|
433
|
+
sglang/srt/layers/quantization/fp8.py,sha256=o_tzYZfgspAuoimcrr_XqcJ9lgBZDuONI8baHtvn3R8,49661
|
434
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=q1dTlGEtdQB3mSvNC5x2lvN23N4WF5eVFCrEf4dQjlI,54875
|
435
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=a4sJaNDCRhS3y9maByEmXj0j3h1hklGw6jiPqEpj_-M,27971
|
436
|
+
sglang/srt/layers/quantization/fpgemm_fp8.py,sha256=dq7rJz-QB9LovmZZLBMK8YJEOr05wjVrtWLmSTkXjYw,7004
|
437
|
+
sglang/srt/layers/quantization/gptq.py,sha256=fBcC-9v9GhLvU_oquKvmjD6O_p725SZPPOUtmDPz66E,39118
|
426
438
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
427
439
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
428
440
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
429
|
-
sglang/srt/layers/quantization/marlin_utils.py,sha256=
|
430
|
-
sglang/srt/layers/quantization/
|
431
|
-
sglang/srt/layers/quantization/
|
432
|
-
sglang/srt/layers/quantization/
|
441
|
+
sglang/srt/layers/quantization/marlin_utils.py,sha256=aM3GU7b7rHNZE-tZjRSrtOaPWzSaMcLxck4he8MlEVI,26344
|
442
|
+
sglang/srt/layers/quantization/marlin_utils_fp8.py,sha256=iSjq-ikPOTU5plrWNTW4MletKLySIrNl5NhQmY6FyAo,12508
|
443
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=1d7ZGQ4_lsfQAVzkNPN_DeVSwWWWEPzWXywO8VIvw-M,52617
|
444
|
+
sglang/srt/layers/quantization/moe_wna16.py,sha256=brU0nG6StgjGuuhOjpeoh-wJVZ1SUgbuHhiDR1hibbw,18905
|
445
|
+
sglang/srt/layers/quantization/mxfp4.py,sha256=v6GlGpvJT2GH75djiJHmz4r-E3SKhvpVD_-UJrHKfUM,31410
|
433
446
|
sglang/srt/layers/quantization/mxfp4_tensor.py,sha256=I1hh_uZqIqkgFnNyjaP17cDMLMV5rs3aFytg91MPhzk,5357
|
434
447
|
sglang/srt/layers/quantization/petit.py,sha256=74Jn0eICq23v_b4rEctDaYTINtbqkdM6IXycT-_FbbI,8954
|
435
448
|
sglang/srt/layers/quantization/petit_utils.py,sha256=-gy4zMhqNoIA1R0n7-5C0efV54jHonCUgPDUUFjGsyM,3245
|
436
449
|
sglang/srt/layers/quantization/qoq.py,sha256=jM96uJfKz3vo1B6SSIrQXNT3vnD3UJrepK2eY-tSQU4,8139
|
437
|
-
sglang/srt/layers/quantization/unquant.py,sha256=
|
438
|
-
sglang/srt/layers/quantization/utils.py,sha256=
|
439
|
-
sglang/srt/layers/quantization/w4afp8.py,sha256=
|
440
|
-
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=
|
441
|
-
sglang/srt/layers/quantization/w8a8_int8.py,sha256=
|
450
|
+
sglang/srt/layers/quantization/unquant.py,sha256=CxsOEYqYIfanKHo0ooFArbVz2ueX3vBWnYHE8gtnzdQ,12996
|
451
|
+
sglang/srt/layers/quantization/utils.py,sha256=DdsHXkB5R8YlzhOIEz9QqxAE8swrH0V9DKsNPrk8GSQ,17969
|
452
|
+
sglang/srt/layers/quantization/w4afp8.py,sha256=345w-gCDes3dGqCUAmjyzXZemsIEWc_swJ7FyJyzFTI,11392
|
453
|
+
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=wzJi5jeTnbf-01iehOVTTCu_262rlMh9AQ2rogKWBmo,9981
|
454
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=33Q_pWBj3l5MoLyrJ0i5hZvn-mCyeskzgS8oRoh72eQ,35138
|
442
455
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
443
456
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=DsPCI82A4rqI6mjKo-WorIKUweppFV7-16Qku-zW9_g,25897
|
444
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
457
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=jWgfDtg5r6IRKJUpYXf5Tp13pWekoUCnYi8LMZ33PcU,25940
|
445
458
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
446
459
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
447
460
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
@@ -601,9 +614,11 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
601
614
|
"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
|
602
615
|
sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
603
616
|
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=FaHKgY9y1oi3zlCmkorSK4r4dhPy7NiviVIhtabvzjM,11536
|
604
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=
|
617
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=ajxS0OUYp2RbHtP3dB71EzsXKQEHMwP4Wo7-pkJZ9u4,771
|
605
618
|
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=On_uvP1ThxgQFAzOWKoteM0vIOHqmtI127A4qbPtmbc,3264
|
606
619
|
sglang/srt/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
620
|
+
sglang/srt/layers/quantization/quark/quark.py,sha256=EqQvWzAc6nd_yl6UIMIwmozKif4I8fRNfBum040UUEQ,14613
|
621
|
+
sglang/srt/layers/quantization/quark/quark_moe.py,sha256=yLRmytEwBMZd7ShzHVX6-w_8koyiRrvIxKx8g02qRZw,6789
|
607
622
|
sglang/srt/layers/quantization/quark/utils.py,sha256=Aq85sXcnVN2IJnfwCe5t9hfkodcDNE9OmxoGwrmzzRE,3487
|
608
623
|
sglang/srt/layers/quantization/quark/schemes/__init__.py,sha256=z1LHBPqkxAS6Wp70DWwESOSixWpIhIQwz1IHcWDdURQ,167
|
609
624
|
sglang/srt/layers/quantization/quark/schemes/quark_scheme.py,sha256=b8-Djo-UQAwgxSWViKDoEP5dOSesnEBPyozX-osB3WY,1478
|
@@ -611,10 +626,10 @@ sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=gMKmrpim
|
|
611
626
|
sglang/srt/lora/layers.py,sha256=3RwD5TC4zO8A2Haz7ScIT5vc_neU9RHM3DoamKttVkw,10838
|
612
627
|
sglang/srt/lora/lora.py,sha256=lPPEJavrfANXDzdmKEg4hbgmKIiEr3NU7KNJeaaKTB8,7393
|
613
628
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
614
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
615
|
-
sglang/srt/lora/lora_registry.py,sha256=
|
616
|
-
sglang/srt/lora/mem_pool.py,sha256=
|
617
|
-
sglang/srt/lora/utils.py,sha256=
|
629
|
+
sglang/srt/lora/lora_manager.py,sha256=FPb-S0qDpCEpO3tv8fuqI7ULznq_UaC8Db2ePJljEBc,20765
|
630
|
+
sglang/srt/lora/lora_registry.py,sha256=osbau-sQZ7BuCeGGpBMFy4w40GO5FGqRgRwDyxxgNmg,8167
|
631
|
+
sglang/srt/lora/mem_pool.py,sha256=FDf9qNEWrZ3yTtrUEvbiUN9FUawRZBlK9l9A2ou5dkU,11242
|
632
|
+
sglang/srt/lora/utils.py,sha256=DePsHi-0S-eCerQeWXTW9U7sG2397w_Bhfs0TAsu4xk,3904
|
618
633
|
sglang/srt/lora/backend/base_backend.py,sha256=hnP7iL6KjOVsH-Sgzj-5AlBAxpwnf37yi-7X_faP3n4,4355
|
619
634
|
sglang/srt/lora/backend/triton_backend.py,sha256=uqwBGlguXX8EkCKjSPqac6SPTgcKA31u3u6HkKPQcos,2530
|
620
635
|
sglang/srt/lora/triton_ops/__init__.py,sha256=JGOYPIn1XbGcyJTbt8A0qoc02PYONSGNNjGkC8yJpAM,283
|
@@ -622,38 +637,38 @@ sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=QURCYxHNR8Ls4SQtt3dvdgjvdDVh
|
|
622
637
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=z9BB84Xu_MjwCu5v9Yvji-FkIzfEjDySAFybc4WYv7A,6483
|
623
638
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=Ksova04wgeGsFqGOXWqJtMYaHgyUYcx8VU42BZQOkVA,5129
|
624
639
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=VqCAFvUtq_l-0RGIkx3W_fzD55QcW2FAcqpvSHOBFp4,5115
|
625
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
640
|
+
sglang/srt/managers/cache_controller.py,sha256=EJX39oikAM5YOkTpqoF-Rg-dFnBW-eWuiFrE88q4_7k,33341
|
626
641
|
sglang/srt/managers/configure_logging.py,sha256=8sNXZ2z9pBWOwn-X3wyz013Ob8Nbm1zDxRkxoZjH-l4,1633
|
627
642
|
sglang/srt/managers/data_parallel_controller.py,sha256=VvEkidmYCGAFTv6upEHf_tyTvkM8xLhCyOnLJGWL6BQ,14592
|
628
|
-
sglang/srt/managers/detokenizer_manager.py,sha256=
|
629
|
-
sglang/srt/managers/io_struct.py,sha256=
|
630
|
-
sglang/srt/managers/mm_utils.py,sha256=
|
643
|
+
sglang/srt/managers/detokenizer_manager.py,sha256=DaVDYaKYLcaTU3Ll4ZJtOdWQGpwbgYcba21JOWOlUBU,10961
|
644
|
+
sglang/srt/managers/io_struct.py,sha256=S7MGa5OvhOB2odBI8eC34fqzMX1QrhNoBPAF4rkGFLc,39403
|
645
|
+
sglang/srt/managers/mm_utils.py,sha256=0Kr3VJKINr9o4k2Tg2KN0Zb9kxRYBd4dxd0ImTbKHw4,29351
|
631
646
|
sglang/srt/managers/multimodal_processor.py,sha256=cnWpu2G79v1a6FJB_FriLxESgGUbfC3GptLmeRVVgew,1801
|
632
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
647
|
+
sglang/srt/managers/schedule_batch.py,sha256=9lhBnf-siQjsThD8FRyhiF50N-LOE7dfoPr1uzklnjQ,77170
|
633
648
|
sglang/srt/managers/schedule_policy.py,sha256=vh9BQW9tBv80LW4JApLE6smU2m4gy6cAEI25HVXiS60,22383
|
634
|
-
sglang/srt/managers/scheduler.py,sha256=
|
649
|
+
sglang/srt/managers/scheduler.py,sha256=RXVUuOLyboWV9NR9U12EhfcJeKfW34fVLFmZGd4OFNA,107583
|
635
650
|
sglang/srt/managers/scheduler_input_blocker.py,sha256=zP8xU_UmU2H0AB6sEqvivDcDB1QDgTauNDYDIJ7Nez4,3683
|
636
651
|
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=-1IOE30eOoTvvpz-Xg9J4UcamwAJle2-odFJ9vrinLE,9341
|
637
652
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=e_l5TRm05liINSAeZU-YPRpJXcutmEWYV30F1vPaxbs,31345
|
638
653
|
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=A67lC_U7HUCf_znatXK51orC8xeFNGouJ866HH_Y-yc,11402
|
639
654
|
sglang/srt/managers/scheduler_recv_skipper.py,sha256=8rVQCBjn9f26Th4XbeUS3fEsvo1GI029Me28wMjcKRY,1103
|
640
655
|
sglang/srt/managers/scheduler_update_weights_mixin.py,sha256=R81fU-0aIJoi5URm9IA-n2sEjvn3phGXOhzJALZjiOM,5467
|
641
|
-
sglang/srt/managers/session_controller.py,sha256=
|
642
|
-
sglang/srt/managers/template_manager.py,sha256=
|
643
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
644
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
656
|
+
sglang/srt/managers/session_controller.py,sha256=FGADRGSkRmS76o_BQ2fivpgw0Q5Q-K0Ws3aezH41YSc,6041
|
657
|
+
sglang/srt/managers/template_manager.py,sha256=m_cy_KY5bOkDlh6IB9ocisy8N5r7abp4nfFnhruNxFg,11947
|
658
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=iy7aH4vugjyHFZl3qAGKWGovuNTn-aokUNb6BShy_1E,84893
|
659
|
+
sglang/srt/managers/tp_worker.py,sha256=n_DqSD4JqOJYjdZrchOpmpuTazRw-AUrs6RPQYuAPyQ,11933
|
645
660
|
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=NXjrBT7lvdUlDDNFzEQyFYCerpqj92sNl2YynGhQj-Y,11118
|
646
|
-
sglang/srt/managers/utils.py,sha256=
|
647
|
-
sglang/srt/mem_cache/allocator.py,sha256=
|
648
|
-
sglang/srt/mem_cache/allocator_ascend.py,sha256=
|
661
|
+
sglang/srt/managers/utils.py,sha256=WbUdADEdiSOoQNfwjfU64mNaXoskEveBO1HP_t0FJtQ,5687
|
662
|
+
sglang/srt/mem_cache/allocator.py,sha256=5cLql3bTIFElYn9S6baBmKCO5L88W_sPC-TsTMZrk_g,18216
|
663
|
+
sglang/srt/mem_cache/allocator_ascend.py,sha256=i0KPCcFlzGkCIjW8ph3IPkBXAWTqq4-AeaoG1wR--lw,4471
|
649
664
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=hLS2ncTMAz7Kpdk5pNwn5c6g8b61_K9OCBL4Vj1xsYc,2801
|
650
665
|
sglang/srt/mem_cache/chunk_cache.py,sha256=xQjfmpijkkNRuqfwYMhoiV2nJAviABX4uOSLE-yyVus,3184
|
651
666
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
652
|
-
sglang/srt/mem_cache/hicache_storage.py,sha256=
|
667
|
+
sglang/srt/mem_cache/hicache_storage.py,sha256=yjXcsoKdjLgqG68E7cHSAQXq08EHgAASr74bZN0Sg7M,6695
|
653
668
|
sglang/srt/mem_cache/hiradix_cache.py,sha256=J-k8HYwJuZlKAFxKWSWvDgaAUp-bgANWH8rr46chnCo,28173
|
654
669
|
sglang/srt/mem_cache/lora_radix_cache.py,sha256=FCA1d-TSqXYPrz9-m-cRrxse9RtwALXltGNuzR-PnB8,14354
|
655
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
656
|
-
sglang/srt/mem_cache/memory_pool_host.py,sha256=
|
670
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=pCcrb7-LNqlVtUonu8X8KMRZZdIgzQfi7ia4QW2eGkY,37086
|
671
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=to15nKPDPq_PwwcIDESUoCMUEowLHH6UMZQmBN2p_8A,26205
|
657
672
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=zPnQLQhBZ6zsUpCQPSoNkrB9EEvpoDQS4mU7c3sRWjE,2171
|
658
673
|
sglang/srt/mem_cache/radix_cache.py,sha256=VdsMPUkaBUjLDTzMqKCwBr1CDP0GlbS_8bJCHrONlk8,19046
|
659
674
|
sglang/srt/mem_cache/radix_cache_cpp.py,sha256=1V-XxYC2jxQYUMJBLrlcSMcqhCBo8TC7wRTTVbOaMkY,9269
|
@@ -662,20 +677,21 @@ sglang/srt/mem_cache/cpp_radix_tree/radix_tree.py,sha256=tQZpz-H6HxNAQe9mYqt6aX8
|
|
662
677
|
sglang/srt/mem_cache/storage/hf3fs/client_hf3fs.py,sha256=WV5M9UPPLUMMjU3Mpp6HBqyCQpGBuMyj-N5PwQcNo5k,5178
|
663
678
|
sglang/srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp,sha256=dDYPtxmL6OFhEyv_GuTgzkTDpBjcD0EK8kphnn7eaGc,1133
|
664
679
|
sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py,sha256=OfQMFwbbQg0pbC7rJktg5wz3YFhNsNOjsXCsAjrh6iU,16738
|
665
|
-
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=
|
680
|
+
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=WcJKrs8uQ9STKc30HYwd6oqT0fGn4UYXQipuEbDvXPw,13145
|
666
681
|
sglang/srt/mem_cache/storage/hf3fs/test_hf3fs_utils.py,sha256=g2h0Woa2CK39pRTigHCVR_hq095dTaC70lCIAIs9THM,1089
|
667
|
-
sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py,sha256=
|
682
|
+
sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py,sha256=UIHykWDBpf1Kld7Fej5Kr9KPQOGeOoVGwtLup3JnuVs,9663
|
668
683
|
sglang/srt/mem_cache/storage/mooncake_store/unit_test.py,sha256=jMdJgU41VscKS-mn_AVZE8LQbb_3MWQ57i9V3OCWLI4,1007
|
669
|
-
sglang/srt/mem_cache/storage/nixl/hicache_nixl.py,sha256=
|
670
|
-
sglang/srt/mem_cache/storage/nixl/nixl_utils.py,sha256=
|
671
|
-
sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py,sha256=
|
684
|
+
sglang/srt/mem_cache/storage/nixl/hicache_nixl.py,sha256=bau9Jsp50lpEiy_osgb-dYzeoUkPWM03x7Q8z2BpKaU,9920
|
685
|
+
sglang/srt/mem_cache/storage/nixl/nixl_utils.py,sha256=KXkwMrbWwIOUOASINnUo4HyheiMd-93smmwGLv0CacU,7463
|
686
|
+
sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py,sha256=vENVvGAd3PqcQEFA812wPoSBYhRemLr8Sfh1LQa0INU,9609
|
672
687
|
sglang/srt/metrics/collector.py,sha256=FH6Wil2lMK7d7q74CfxfdULCaHKDXeAoo8UBZqqdepM,20289
|
673
688
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
674
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
675
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
676
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
689
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=vFIR-DMVfyBPQIlHX3spaoPsXbx2RCC3h77vHmhb2e0,33896
|
690
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=2KBu9SChR-YwSNbw1mO3WR0P_EGQjFUC5rQfBx6js90,40707
|
691
|
+
sglang/srt/model_executor/model_runner.py,sha256=FJYnyFsy6UqX3ZTZQZz0alyVGj8zs9IlSmQn9AfNAj0,78564
|
692
|
+
sglang/srt/model_executor/npu_graph_runner.py,sha256=isp2Plkf4b_gdjptYxJhTJk7JL21Jg-Md3hAYIuSVxM,3424
|
677
693
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
678
|
-
sglang/srt/model_loader/loader.py,sha256=
|
694
|
+
sglang/srt/model_loader/loader.py,sha256=GPKjMkulnIqlX7gdSSpSselsXLpbEtCLscleC85-1jM,60879
|
679
695
|
sglang/srt/model_loader/utils.py,sha256=svSrPQxViBz_-0_sByu4coCYrzJ51-4FCi_bFqa6rDo,4474
|
680
696
|
sglang/srt/model_loader/weight_utils.py,sha256=dHEkm0c4w-lyhJBzktvmop-Psmkpb2KoTu7Azgw7VgU,38555
|
681
697
|
sglang/srt/models/arcee.py,sha256=Q6fujRESEnljzs8ls3XGsPtWxzfKfUa0QAvAekYzeBY,18981
|
@@ -685,13 +701,13 @@ sglang/srt/models/bert.py,sha256=ODJe8YfNRP-hHsomFWk4_QpcuiSsNfjzGf256EDS0Pc,158
|
|
685
701
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
686
702
|
sglang/srt/models/clip.py,sha256=kOPSXnmgH_QKu2-ENn49HLDS9yf7Gm1HCOE_YvoNhlA,19858
|
687
703
|
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
688
|
-
sglang/srt/models/dbrx.py,sha256=
|
689
|
-
sglang/srt/models/deepseek.py,sha256=
|
704
|
+
sglang/srt/models/dbrx.py,sha256=117gwrB_o8VlACwDH5YlXkPfuS7t2Mh-nyJvpNpIYxs,15903
|
705
|
+
sglang/srt/models/deepseek.py,sha256=M7nyHcAbTIs8vc1g6u00oy22-pp704Xp4T3clBzu4xM,17460
|
690
706
|
sglang/srt/models/deepseek_janus_pro.py,sha256=td8xGs6ARfJ8AQCYwUhMOZoWigrAs7m3trF5-kXCqik,70418
|
691
|
-
sglang/srt/models/deepseek_nextn.py,sha256=
|
692
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
707
|
+
sglang/srt/models/deepseek_nextn.py,sha256=uoiJxAVl9DX7bQcjyuouAZz6W-cB1HMubcirTBghyR4,6115
|
708
|
+
sglang/srt/models/deepseek_v2.py,sha256=_4TH56N-VT1uguhGHI3DKHm9C9PPDQNaQInER3AhKC0,106616
|
693
709
|
sglang/srt/models/deepseek_vl2.py,sha256=7X3gI4DE7guUtNJvMLf06jO8MUHKa2Aan8evZg5hsXc,13061
|
694
|
-
sglang/srt/models/ernie4.py,sha256=
|
710
|
+
sglang/srt/models/ernie4.py,sha256=7dP7_d0i86tv8Mp21Ew9RdsFr6TskIkm8UtUd8zFo00,16067
|
695
711
|
sglang/srt/models/ernie4_eagle.py,sha256=E7f-ygCcY8pIoyTMKFyVC2uRcG59-_RaQTO4gd5_uWI,7223
|
696
712
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
697
713
|
sglang/srt/models/gemma.py,sha256=2atKwFN5wCsJCmBRmURX9vaCcFjxlFirL7xsnG5KPlI,14180
|
@@ -703,26 +719,26 @@ sglang/srt/models/gemma3n_audio.py,sha256=isgKfjA5UieYawxU6medL2ssXlzYPqAbagDBnL
|
|
703
719
|
sglang/srt/models/gemma3n_causal.py,sha256=kBDlpSWAg6ZDmUPe08Q7sj5CbdVD_0h07zwJw8sKu7I,36335
|
704
720
|
sglang/srt/models/gemma3n_mm.py,sha256=XTY3HIUt4xv407aS_2rXdfxD3G1sp4z2kVhdC4vnxIQ,20354
|
705
721
|
sglang/srt/models/glm4.py,sha256=dijzVTTgg8zyJ3gga95MKY0WwqwnuAaf-VIV93OFAmc,11433
|
706
|
-
sglang/srt/models/glm4_moe.py,sha256=
|
722
|
+
sglang/srt/models/glm4_moe.py,sha256=PkDR3VEG2e4pl4cwSYJ6WzlYVmN6kwaSKg1Fg-wcphk,41723
|
707
723
|
sglang/srt/models/glm4_moe_nextn.py,sha256=EuDWOBSd0oFfdvloePlpzAL81M_L7oz0BiWm74RQioc,5943
|
708
|
-
sglang/srt/models/glm4v.py,sha256=
|
709
|
-
sglang/srt/models/glm4v_moe.py,sha256=
|
724
|
+
sglang/srt/models/glm4v.py,sha256=WtDvH4691H6IKrcGBrkBpweSm_iFK61bMEfvqpbblmc,23790
|
725
|
+
sglang/srt/models/glm4v_moe.py,sha256=qgJtWyRI0dy9qcTMXHxhBZp-ghfghV3PLhpOXgSAW60,17313
|
710
726
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
711
727
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
712
|
-
sglang/srt/models/gpt_oss.py,sha256=
|
728
|
+
sglang/srt/models/gpt_oss.py,sha256=qXa6BAm8gBTuCSX0ax3Iz4SkIIko0s1u8sVu8kJVzkY,44930
|
713
729
|
sglang/srt/models/granite.py,sha256=8q92shxVPAp_cJDohJATffSGd7Z0Oi-vF5jpY6DlK4s,19840
|
714
|
-
sglang/srt/models/granitemoe.py,sha256=
|
715
|
-
sglang/srt/models/grok.py,sha256=
|
730
|
+
sglang/srt/models/granitemoe.py,sha256=j1rgZ62CbBioECjUblDCw_NneDQgY_QJODsI0fqXVO8,13779
|
731
|
+
sglang/srt/models/grok.py,sha256=Va-kPr1XxjK4jWhVkvqzRl3e6OWuGZnbhp1TadadkeQ,40679
|
716
732
|
sglang/srt/models/hunyuan.py,sha256=RSZErx-Swt65kmfvSXJQJJ6KhjucuNY4UUVLWC8hWaA,31102
|
717
733
|
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
718
734
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
719
735
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
720
|
-
sglang/srt/models/interns1.py,sha256=
|
721
|
-
sglang/srt/models/internvl.py,sha256=
|
736
|
+
sglang/srt/models/interns1.py,sha256=E4SyJWocXZ5rAuAV8kj569OHo57r04W4hmq1CF6oiFs,12516
|
737
|
+
sglang/srt/models/internvl.py,sha256=uMM-FLZDP5QG5hk3OjA5bshAaxVCxHQ7RFUXrd5_EdU,25736
|
722
738
|
sglang/srt/models/kimi_vl.py,sha256=XulRiufQzOSWZe8-bUl2OEdznvsVU9OBsEYipaX3YkM,12877
|
723
739
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
724
740
|
sglang/srt/models/llama.py,sha256=tdyUon6icwzqo4XTAkFxVA2f82g80AGr9ZezK1uXmkM,28126
|
725
|
-
sglang/srt/models/llama4.py,sha256=
|
741
|
+
sglang/srt/models/llama4.py,sha256=Fp5kqnk1v9Q1TOZH6uXkFKOOZLjV-B6FGoWpw7icO9I,19598
|
726
742
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
727
743
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
728
744
|
sglang/srt/models/llama_eagle3.py,sha256=715soylDE3kOMWskbPy_70BFxaSc5ptaHCS1v3-ViA0,8579
|
@@ -733,59 +749,60 @@ sglang/srt/models/llavavid.py,sha256=-CSk0RJ2MQeb81sh-RISeVJFaI-XWY6nR6_I594MkME
|
|
733
749
|
sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
734
750
|
sglang/srt/models/mimo_mtp.py,sha256=jSmqJAXu7G3OO7jW1oa2suI4H_Yl7u5ZT7w4lHFbHhg,7292
|
735
751
|
sglang/srt/models/minicpm.py,sha256=CzBJyZtfMpp8jvlEl29DHI7HLVq-CxuqP1UHwxIbaUI,14567
|
736
|
-
sglang/srt/models/minicpm3.py,sha256=
|
752
|
+
sglang/srt/models/minicpm3.py,sha256=Cflu4Tb2hxpjapRBZ5n4kX8a1nnFwffK-M8uHPRUra4,19276
|
737
753
|
sglang/srt/models/minicpmo.py,sha256=st8I13Ere5RkRHHQQN1LgZh1ybUA3_buxaaE4XlV8ag,76123
|
738
754
|
sglang/srt/models/minicpmv.py,sha256=g4aAOG8PVGkZqGmlneVaScAtNpSLqSVbZGRAikyrBy8,30394
|
739
755
|
sglang/srt/models/mistral.py,sha256=ni7PppA_5X4ivTnIps3yoEaMEL-G6Gaf9b5hGC1vU5Q,3475
|
740
|
-
sglang/srt/models/mixtral.py,sha256=
|
756
|
+
sglang/srt/models/mixtral.py,sha256=ohZVFJ75QWuE2kBKD7Sd4fcx9YbbjA7JxnYAsOIfORU,17166
|
741
757
|
sglang/srt/models/mixtral_quant.py,sha256=UUIq7lpUonD9IoGePyl59oJYEcVwT9wUXvtVp5tjQ9Y,15406
|
742
758
|
sglang/srt/models/mllama.py,sha256=OdX7brhyfGiMFPulxF77QOUi-Kcscg3Qo4ipyxzs9yA,39670
|
743
759
|
sglang/srt/models/mllama4.py,sha256=eWjuYA7GZ6NrPFFr_qkA1JC5yRHrQ_oKnoelWTyDvp4,34745
|
760
|
+
sglang/srt/models/nemotron_nas.py,sha256=CoSAKqlbej4Xe30uY4w76iASBqeuJf8-imisDK00zEU,15964
|
744
761
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
745
762
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
746
|
-
sglang/srt/models/olmoe.py,sha256=
|
763
|
+
sglang/srt/models/olmoe.py,sha256=zryYUQEhEdhd6xcR_HyLV7gHCcKt-HWHeEeIUqmhmcc,16100
|
747
764
|
sglang/srt/models/persimmon.py,sha256=86Duo3HiZqDj9O2UzWbJgUEhQOXzGBUdhUofQhcs1VE,11244
|
748
765
|
sglang/srt/models/phi.py,sha256=n6A1d47MvnR1lmSsZ3TuzXk5kT1Lntj_YQ5uNvR0s5o,10287
|
749
766
|
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
750
|
-
sglang/srt/models/phi4mm.py,sha256=
|
767
|
+
sglang/srt/models/phi4mm.py,sha256=TKOFM4k8o_JGwYM5mBb2hHbbOMLjbveu5izIHCbT7ug,20617
|
751
768
|
sglang/srt/models/phi4mm_audio.py,sha256=0ChekwoYudAnbY0-JyNwz_inzMlxM8FmULqR9mwkPhQ,48877
|
752
769
|
sglang/srt/models/phi4mm_utils.py,sha256=bW3un4x3SHDvSkAOHQEFO286FGdOPeKhBpJCOmNlC9E,66956
|
753
770
|
sglang/srt/models/phimoe.py,sha256=EGaKFi02MZP20qFrILA4o2SJ0wb1HoJagFTSqVUbJcQ,19223
|
754
771
|
sglang/srt/models/pixtral.py,sha256=ZkZrV0mEfmbBdgRko2AvsMFZbAVskgp_5a5p1xCSRN0,16835
|
755
772
|
sglang/srt/models/qwen.py,sha256=j0OU3JjznWi_TbayI09yYGM-Obov6mQzJO82Hs0qBGw,11868
|
756
773
|
sglang/srt/models/qwen2.py,sha256=TuKblSvilyVoq9en9e9YpwzLGkpDeOA6IWJELOYSzZA,22733
|
757
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
774
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=3nRfXL-L230Ml_O3tYv5CbU6paT9ZS1QdfdVWblowIk,22892
|
758
775
|
sglang/srt/models/qwen2_audio.py,sha256=SOOsspU7J6eM-iSkms5op0nWhoxJd6QxmwXU2aQBEEQ,7776
|
759
776
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
760
777
|
sglang/srt/models/qwen2_eagle.py,sha256=6spFg6JYQGeUXLv2Q5eMkVzZvnqGyvW6SdVBtFMxlTM,4806
|
761
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
778
|
+
sglang/srt/models/qwen2_moe.py,sha256=lyaNhrUsmg6OyF9LAe4J1csQIWOTzNNihRkdjMEw8CE,25971
|
762
779
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
763
780
|
sglang/srt/models/qwen2_vl.py,sha256=ZRAL32Ymt4ZCBqB0JorXAm4ZBrECZ9EbaXKaTSikkQM,21366
|
764
|
-
sglang/srt/models/qwen3.py,sha256=
|
765
|
-
sglang/srt/models/qwen3_classification.py,sha256=
|
766
|
-
sglang/srt/models/qwen3_moe.py,sha256=
|
781
|
+
sglang/srt/models/qwen3.py,sha256=xw-OsNRsC3nO5IR2OG7nSfupIiKQOxC_0VFQ4lKcbfc,19123
|
782
|
+
sglang/srt/models/qwen3_classification.py,sha256=bdjAylXJCjXKjAho74nmtIMpEG0Af98N-aZQ-pKKMY0,3262
|
783
|
+
sglang/srt/models/qwen3_moe.py,sha256=MtvaiBMR_Yd0QFR8gJ3fOrn62fVoU7HhYRvrlrj0R9U,32314
|
767
784
|
sglang/srt/models/registry.py,sha256=kKQ5ruD6_c3JxWsykOoxt-hroSlslv-Niz0nYvHrhGg,3779
|
768
785
|
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
769
786
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
770
787
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
771
|
-
sglang/srt/models/step3_vl.py,sha256=
|
788
|
+
sglang/srt/models/step3_vl.py,sha256=joJmGukbGThLvwwbwrI4mCEVONH_U1dzFLWdpeJFoKo,35654
|
772
789
|
sglang/srt/models/torch_native_llama.py,sha256=C1WpLn47q0l7IQa0k-Gvbs914FBcpKzqTIX-uvibq-w,18320
|
773
790
|
sglang/srt/models/transformers.py,sha256=ChqRbUq5YD9oXnXwVP81XRoZmsKc44ouYDNgRsH6zmk,10249
|
774
791
|
sglang/srt/models/vila.py,sha256=3NiRHWOqXnCRjXmswAldsNtiE5zRILbScEsbhUzLZF4,9846
|
775
792
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
776
|
-
sglang/srt/models/xverse_moe.py,sha256=
|
793
|
+
sglang/srt/models/xverse_moe.py,sha256=nBtG_PAK8wcp1tW2l2Zby2oEOmtWAYzH5COH-_N5IAM,17072
|
777
794
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
778
795
|
sglang/srt/multimodal/mm_utils.py,sha256=6bV1_a7Iet9W0y3qdd0E-hFM78zalIzNZCYbLzJX2y8,12640
|
779
|
-
sglang/srt/multimodal/processors/base_processor.py,sha256=
|
796
|
+
sglang/srt/multimodal/processors/base_processor.py,sha256=ZLLNjSUaiDCujQQmGhIO8kHXAQT8Acux7CRR2Y-Yjik,24464
|
780
797
|
sglang/srt/multimodal/processors/clip.py,sha256=5nXZuQYbyf-5mlqPwjhQrlWqxvswImWZQXivChsiHfQ,1057
|
781
798
|
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=Pymag9f0U5L_bBOTFs2q94BbuPJ-VwqSixs3meO0nsM,2569
|
782
799
|
sglang/srt/multimodal/processors/gemma3.py,sha256=7aD6cR60iSC_MqjzdCDMAgtrb_cmy9YJyqLgVRClBT8,1986
|
783
800
|
sglang/srt/multimodal/processors/gemma3n.py,sha256=mtmvBasOMxb3Y2NLZR02nMYX30RLUXhDYJ5uVOElr10,2776
|
784
801
|
sglang/srt/multimodal/processors/glm4v.py,sha256=7VcbNhnCdhqsvLAajtZJtdwOtDTwy4M7UqVMO5ofowU,4916
|
785
|
-
sglang/srt/multimodal/processors/internvl.py,sha256=
|
802
|
+
sglang/srt/multimodal/processors/internvl.py,sha256=Gn4hAK2UxhDKACwp1IE6P-hp6pf1q_qgTuviSkx-S30,10029
|
786
803
|
sglang/srt/multimodal/processors/janus_pro.py,sha256=_4ltWmdtFjbh1VCMRbcgxW61eWIABIzHG-YgwHWaYq8,1471
|
787
804
|
sglang/srt/multimodal/processors/kimi_vl.py,sha256=5i8KmGxnnDtQc7XqUBNyanAfGxhxj8iRFBFONHmpiFg,1565
|
788
|
-
sglang/srt/multimodal/processors/llava.py,sha256
|
805
|
+
sglang/srt/multimodal/processors/llava.py,sha256=-YtDc_7TsMWmwKkD4KJZW2Y0jPFlZtbQ38K_N24hk0w,8231
|
789
806
|
sglang/srt/multimodal/processors/minicpm.py,sha256=ysJlUaxcBcWjKliz5VmXKVv0ec4QWRHXZk4ga-hXVf0,5354
|
790
807
|
sglang/srt/multimodal/processors/mlama.py,sha256=FgPm2JQzfPFDcGYDm0mqfDfO_eJKy-NiVgF-vId6w8Y,1233
|
791
808
|
sglang/srt/multimodal/processors/mllama4.py,sha256=1YGETKSzMZIa7BOwq3T9cbsYjUcW5sopcpc9JNJ000g,1911
|
@@ -804,11 +821,12 @@ sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4T
|
|
804
821
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
805
822
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
806
823
|
sglang/srt/speculative/build_eagle_tree.py,sha256=O9LJNaBflgJdWT94D-rGH1gJFJ18nst2oOD8HnA2mZ4,12859
|
807
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=
|
824
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=jOIQDXsZ_CbxiTXnJjKtzYfOpc7-67dWwCaNcrv1Ebc,13938
|
808
825
|
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=QuPI0S85KirTlJArLpJXpywv7XQLborDGLFYwLUBnwk,15459
|
809
|
-
sglang/srt/speculative/eagle_utils.py,sha256=
|
810
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
826
|
+
sglang/srt/speculative/eagle_utils.py,sha256=H-2aqm3REztUXLnmhi31ck3TWPPMVKc2CUkWBPsFK44,47785
|
827
|
+
sglang/srt/speculative/eagle_worker.py,sha256=tvRV7JNvIeOFb3CTF756kRxQm8SZwfA7rCmm39feMiA,41451
|
811
828
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
829
|
+
sglang/srt/tokenizer/tiktoken_tokenizer.py,sha256=su5woRjUNJEOGmi41LiUw__LmzyNIC-UiBikk-B8W90,6158
|
812
830
|
sglang/srt/weight_sync/tensor_bucket.py,sha256=vp_LRrhULNnxiw9Tf56FcEckgUg07lifgv1lasG6y7o,3695
|
813
831
|
sglang/srt/weight_sync/utils.py,sha256=43zl3u8Svzj49p7Sk78xp7SWW83mlr3EH-OZFGUGy5w,4157
|
814
832
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
@@ -816,7 +834,7 @@ sglang/test/doc_patch.py,sha256=P9PYjBIVlZHvP9M34qS-8m1scmDP27ciNJNvZOdrUKE,1614
|
|
816
834
|
sglang/test/few_shot_gsm8k.py,sha256=e7NgJLJi3o7uPKUfBF1O9oueKWxLzZ_9bx1xFaEWX3M,4305
|
817
835
|
sglang/test/few_shot_gsm8k_engine.py,sha256=h88s3HzEStA1zjQkR-AgIEOQMwJMSnPHkX_wGBWXUYw,3907
|
818
836
|
sglang/test/run_eval.py,sha256=VnbcmUhceDUU3-nXlZ6uQMM3MEvnZh1gzP3LXxYkuxc,4251
|
819
|
-
sglang/test/runners.py,sha256=
|
837
|
+
sglang/test/runners.py,sha256=uwLTGqSquJi5Js-FfkDB9ofsgNQYblV_n7wz7sPL3ww,33908
|
820
838
|
sglang/test/send_one.py,sha256=XNZdfZs21tXDBwrDj2pq46WQd5smiKoYETY8U09c1Z8,5079
|
821
839
|
sglang/test/simple_eval_common.py,sha256=B60Yi3ox2Yubsq8M3BbApQTfmLhwQoL4ciS2ac12SM4,12702
|
822
840
|
sglang/test/simple_eval_gpqa.py,sha256=M6hpPs8l2Z4wUiyE7rCU1zyKoImXB4Z395Hgz43uvvQ,3293
|
@@ -825,27 +843,27 @@ sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWU
|
|
825
843
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
826
844
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
827
845
|
sglang/test/test_activation.py,sha256=bDBFl4Y30siXj7Ifl66fc2HytOrcZdHFiP2i9K8TIsY,3140
|
828
|
-
sglang/test/test_block_fp8.py,sha256=
|
846
|
+
sglang/test/test_block_fp8.py,sha256=mOM-eX9LisotPlMLSCvH4XwWMbvNpVOBtt7euXuVTDw,21842
|
829
847
|
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7Xx0MjOoOBYL8J7ETvOVA,8180
|
830
|
-
sglang/test/test_block_fp8_ep.py,sha256=
|
848
|
+
sglang/test/test_block_fp8_ep.py,sha256=n4X6ZKwuUUbV5Ofjg64ptlaFGI1LbRXDfFiJW1ELHgY,10546
|
831
849
|
sglang/test/test_custom_ops.py,sha256=PenQ8zM1wj5xwiVEPVzD37pO-x90aOfFMpCRZenaKsY,5709
|
832
|
-
sglang/test/test_cutlass_moe.py,sha256=
|
833
|
-
sglang/test/test_cutlass_w4a8_moe.py,sha256=
|
850
|
+
sglang/test/test_cutlass_moe.py,sha256=fhAZlJmTMwhw7FYgSoYggAvXArE8mqluU6qO5NDLHDE,9835
|
851
|
+
sglang/test/test_cutlass_w4a8_moe.py,sha256=E0ffQOR84bEFz6KFNbczH2LRhQqkeC9HPp76u0vzdwo,8809
|
834
852
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
835
853
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
836
|
-
sglang/test/test_fp4_moe.py,sha256=
|
854
|
+
sglang/test/test_fp4_moe.py,sha256=rJLkKW3glBMvI5Ed0LltOHi8zCReMa-WB50p5zGm6J4,10189
|
837
855
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
838
856
|
sglang/test/test_marlin_moe.py,sha256=TOuYlVMx2Lv_IN3AMWsg5aGaxQF472E1B9ev_vvfU2Q,7971
|
839
857
|
sglang/test/test_marlin_utils.py,sha256=kC7IzN364mJT9xw0nKUP1V1OK1hkw6fQTBvD4nRaOz4,5151
|
840
858
|
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
841
|
-
sglang/test/test_utils.py,sha256=
|
859
|
+
sglang/test/test_utils.py,sha256=MiIxaKPhzHXDgzW2w9B8hhRk9jtXn2HOj81lLgEtf2Q,41530
|
842
860
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
843
861
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
844
862
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
845
863
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
846
864
|
sglang/test/attention/test_trtllm_mla_backend.py,sha256=ilrX20-1hVo0nmKN0GTqzKoUmDarTXGS8nWJ6c8RHVY,41792
|
847
|
-
sglang-0.5.
|
848
|
-
sglang-0.5.
|
849
|
-
sglang-0.5.
|
850
|
-
sglang-0.5.
|
851
|
-
sglang-0.5.
|
865
|
+
sglang-0.5.1.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
866
|
+
sglang-0.5.1.dist-info/METADATA,sha256=ay7jXrW9PA-uzilMp3qXaFmXLVietplAqnH1Buh4l8c,27609
|
867
|
+
sglang-0.5.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
868
|
+
sglang-0.5.1.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
869
|
+
sglang-0.5.1.dist-info/RECORD,,
|