sglang 0.4.8__py3-none-any.whl → 0.4.9__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- sglang/bench_one_batch_server.py +17 -2
- sglang/bench_serving.py +168 -22
- sglang/srt/configs/internvl.py +4 -2
- sglang/srt/configs/janus_pro.py +1 -1
- sglang/srt/configs/model_config.py +49 -0
- sglang/srt/configs/update_config.py +119 -0
- sglang/srt/conversation.py +35 -0
- sglang/srt/custom_op.py +7 -1
- sglang/srt/disaggregation/base/conn.py +2 -0
- sglang/srt/disaggregation/decode.py +22 -6
- sglang/srt/disaggregation/mooncake/conn.py +289 -48
- sglang/srt/disaggregation/mooncake/transfer_engine.py +31 -1
- sglang/srt/disaggregation/nixl/conn.py +100 -52
- sglang/srt/disaggregation/prefill.py +5 -4
- sglang/srt/disaggregation/utils.py +13 -12
- sglang/srt/distributed/parallel_state.py +44 -17
- sglang/srt/entrypoints/EngineBase.py +8 -0
- sglang/srt/entrypoints/engine.py +45 -9
- sglang/srt/entrypoints/http_server.py +111 -24
- sglang/srt/entrypoints/openai/protocol.py +51 -6
- sglang/srt/entrypoints/openai/serving_chat.py +52 -76
- sglang/srt/entrypoints/openai/serving_completions.py +1 -0
- sglang/srt/entrypoints/openai/serving_embedding.py +1 -0
- sglang/srt/eplb/__init__.py +0 -0
- sglang/srt/{managers → eplb}/eplb_algorithms/__init__.py +1 -1
- sglang/srt/{managers → eplb}/eplb_manager.py +2 -4
- sglang/srt/{eplb_simulator → eplb/eplb_simulator}/reader.py +1 -1
- sglang/srt/{managers → eplb}/expert_distribution.py +18 -1
- sglang/srt/{managers → eplb}/expert_location.py +1 -1
- sglang/srt/{managers → eplb}/expert_location_dispatch.py +1 -1
- sglang/srt/{model_executor → eplb}/expert_location_updater.py +17 -1
- sglang/srt/hf_transformers_utils.py +2 -1
- sglang/srt/layers/activation.py +7 -0
- sglang/srt/layers/amx_utils.py +86 -0
- sglang/srt/layers/attention/ascend_backend.py +219 -0
- sglang/srt/layers/attention/flashattention_backend.py +56 -23
- sglang/srt/layers/attention/tbo_backend.py +37 -9
- sglang/srt/layers/communicator.py +18 -2
- sglang/srt/layers/dp_attention.py +9 -3
- sglang/srt/layers/elementwise.py +76 -12
- sglang/srt/layers/flashinfer_comm_fusion.py +202 -0
- sglang/srt/layers/layernorm.py +41 -0
- sglang/srt/layers/linear.py +99 -12
- sglang/srt/layers/logits_processor.py +15 -6
- sglang/srt/layers/moe/ep_moe/kernels.py +23 -8
- sglang/srt/layers/moe/ep_moe/layer.py +115 -25
- sglang/srt/layers/moe/ep_moe/token_dispatcher.py +42 -19
- sglang/srt/layers/moe/fused_moe_native.py +7 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +8 -4
- sglang/srt/layers/moe/fused_moe_triton/layer.py +129 -10
- sglang/srt/layers/moe/router.py +60 -22
- sglang/srt/layers/moe/topk.py +36 -28
- sglang/srt/layers/parameter.py +67 -7
- sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py +1 -1
- sglang/srt/layers/quantization/fp8.py +44 -0
- sglang/srt/layers/quantization/fp8_kernel.py +1 -1
- sglang/srt/layers/quantization/fp8_utils.py +6 -6
- sglang/srt/layers/quantization/gptq.py +5 -1
- sglang/srt/layers/quantization/moe_wna16.py +1 -1
- sglang/srt/layers/quantization/quant_utils.py +166 -0
- sglang/srt/layers/quantization/w8a8_int8.py +52 -1
- sglang/srt/layers/rotary_embedding.py +105 -13
- sglang/srt/layers/vocab_parallel_embedding.py +19 -2
- sglang/srt/lora/lora.py +4 -5
- sglang/srt/lora/lora_manager.py +73 -20
- sglang/srt/managers/configure_logging.py +1 -1
- sglang/srt/managers/io_struct.py +60 -15
- sglang/srt/managers/mm_utils.py +73 -59
- sglang/srt/managers/multimodal_processor.py +2 -6
- sglang/srt/managers/multimodal_processors/qwen_audio.py +94 -0
- sglang/srt/managers/schedule_batch.py +80 -79
- sglang/srt/managers/scheduler.py +153 -63
- sglang/srt/managers/scheduler_output_processor_mixin.py +8 -2
- sglang/srt/managers/session_controller.py +12 -3
- sglang/srt/managers/tokenizer_manager.py +314 -103
- sglang/srt/managers/tp_worker.py +13 -1
- sglang/srt/managers/tp_worker_overlap_thread.py +8 -0
- sglang/srt/mem_cache/allocator.py +290 -0
- sglang/srt/mem_cache/chunk_cache.py +34 -2
- sglang/srt/mem_cache/memory_pool.py +289 -3
- sglang/srt/mem_cache/multimodal_cache.py +3 -0
- sglang/srt/model_executor/cuda_graph_runner.py +3 -2
- sglang/srt/model_executor/forward_batch_info.py +17 -4
- sglang/srt/model_executor/model_runner.py +302 -58
- sglang/srt/model_loader/loader.py +86 -10
- sglang/srt/model_loader/weight_utils.py +160 -3
- sglang/srt/models/deepseek_nextn.py +5 -4
- sglang/srt/models/deepseek_v2.py +305 -26
- sglang/srt/models/deepseek_vl2.py +3 -5
- sglang/srt/models/gemma3_causal.py +1 -2
- sglang/srt/models/gemma3n_audio.py +949 -0
- sglang/srt/models/gemma3n_causal.py +1010 -0
- sglang/srt/models/gemma3n_mm.py +495 -0
- sglang/srt/models/hunyuan.py +771 -0
- sglang/srt/models/kimi_vl.py +1 -2
- sglang/srt/models/llama.py +10 -4
- sglang/srt/models/llama4.py +32 -45
- sglang/srt/models/llama_eagle3.py +61 -11
- sglang/srt/models/llava.py +5 -5
- sglang/srt/models/minicpmo.py +2 -2
- sglang/srt/models/mistral.py +1 -1
- sglang/srt/models/mllama4.py +43 -11
- sglang/srt/models/phi4mm.py +1 -3
- sglang/srt/models/pixtral.py +3 -7
- sglang/srt/models/qwen2.py +31 -3
- sglang/srt/models/qwen2_5_vl.py +1 -3
- sglang/srt/models/qwen2_audio.py +200 -0
- sglang/srt/models/qwen2_moe.py +32 -6
- sglang/srt/models/qwen2_vl.py +1 -4
- sglang/srt/models/qwen3.py +94 -25
- sglang/srt/models/qwen3_moe.py +68 -21
- sglang/srt/models/vila.py +3 -8
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/base_processor.py +150 -133
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/clip.py +2 -13
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/deepseek_vl_v2.py +4 -11
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/gemma3.py +3 -10
- sglang/srt/multimodal/processors/gemma3n.py +82 -0
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/internvl.py +3 -10
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/janus_pro.py +3 -9
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/kimi_vl.py +6 -13
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/llava.py +2 -10
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/minicpm.py +5 -12
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/mlama.py +2 -14
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/mllama4.py +3 -6
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/phi4mm.py +4 -14
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/pixtral.py +3 -9
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/qwen_vl.py +8 -14
- sglang/srt/{managers/multimodal_processors → multimodal/processors}/vila.py +13 -31
- sglang/srt/operations_strategy.py +6 -2
- sglang/srt/reasoning_parser.py +26 -0
- sglang/srt/sampling/sampling_batch_info.py +39 -1
- sglang/srt/server_args.py +85 -24
- sglang/srt/speculative/build_eagle_tree.py +57 -18
- sglang/srt/speculative/eagle_worker.py +6 -4
- sglang/srt/two_batch_overlap.py +204 -28
- sglang/srt/utils.py +369 -138
- sglang/srt/warmup.py +12 -3
- sglang/test/runners.py +10 -1
- sglang/test/test_utils.py +15 -3
- sglang/version.py +1 -1
- {sglang-0.4.8.dist-info → sglang-0.4.9.dist-info}/METADATA +9 -6
- {sglang-0.4.8.dist-info → sglang-0.4.9.dist-info}/RECORD +149 -137
- sglang/math_utils.py +0 -8
- /sglang/srt/{managers → eplb}/eplb_algorithms/deepseek.py +0 -0
- /sglang/srt/{managers → eplb}/eplb_algorithms/deepseek_vec.py +0 -0
- /sglang/srt/{eplb_simulator → eplb/eplb_simulator}/__init__.py +0 -0
- /sglang/srt/{mm_utils.py → multimodal/mm_utils.py} +0 -0
- {sglang-0.4.8.dist-info → sglang-0.4.9.dist-info}/WHEEL +0 -0
- {sglang-0.4.8.dist-info → sglang-0.4.9.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.8.dist-info → sglang-0.4.9.dist-info}/top_level.txt +0 -0
@@ -2,16 +2,15 @@ sglang/__init__.py,sha256=x1v8748WXS2BAptWAd5fR3YBEkngC7e_P_rkCNuNCGg,1702
|
|
2
2
|
sglang/api.py,sha256=rcp3GeoyZhmJ0GDLPRkuZNcxd0TBJy_wfUDpcmQoqW8,7210
|
3
3
|
sglang/bench_offline_throughput.py,sha256=TwgXZYmwPaHVsdPtNU9LO0p1tr5OOKLy9wYgrfGAlFU,14056
|
4
4
|
sglang/bench_one_batch.py,sha256=RJsXQ7pvq8y4yzW7svURtWZF5RiawxEMrsjV0OcKsrk,19388
|
5
|
-
sglang/bench_one_batch_server.py,sha256=
|
6
|
-
sglang/bench_serving.py,sha256=
|
5
|
+
sglang/bench_one_batch_server.py,sha256=LS1BRmFwP67IpYlU5wmkWjqquiA5drvtWe-fwHnFSKI,14170
|
6
|
+
sglang/bench_serving.py,sha256=sQKEgJZIfHRu3vNh8QWqIrTQzOfUMaoVidG05ewTVUE,71744
|
7
7
|
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
8
8
|
sglang/compile_deep_gemm.py,sha256=H118s76CKdpZr-cDeFfBCePe7--c_teEBNVIzchYVSo,6243
|
9
9
|
sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
|
10
10
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
11
|
-
sglang/math_utils.py,sha256=QYtbaIA76P33ojcOrL32VR6yXWv-Od_3WCZNO4kQ-YQ,177
|
12
11
|
sglang/profiler.py,sha256=tEHzHerXC-ymk4OrkoUcMbgcGHmb8VESthsNSP2Yx9w,4417
|
13
12
|
sglang/utils.py,sha256=VH6zrnkjzcR3DE__WfVph6wswJ4JuzoQD47VmbZ38eI,16435
|
14
|
-
sglang/version.py,sha256=
|
13
|
+
sglang/version.py,sha256=LdxLMJM_JXsCQBeSvnxCNyGWmINE0yWfna3DQaT41Vs,22
|
15
14
|
sglang/eval/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
16
15
|
sglang/eval/loogle_eval.py,sha256=pRPVA4fxGmT3_oXvXnlNE-UlPrcQGLBJF-OSE9YWJXM,4336
|
17
16
|
sglang/lang/chat_template.py,sha256=HKlx7snSWFED8GKF5ex79sQrPWFw5TSXQM0_LsiD9Bc,20552
|
@@ -31,34 +30,34 @@ sglang/srt/_custom_ops.py,sha256=0lJRMTKTjoxJPh1qQnnMY02Z3SyBDi7LJI34IBLQsgQ,446
|
|
31
30
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
32
31
|
sglang/srt/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
33
32
|
sglang/srt/constants.py,sha256=0i-tEwG2BSYNDy96MxnGHV5HnBELkYcnsVGsE-R18o0,93
|
34
|
-
sglang/srt/conversation.py,sha256=
|
35
|
-
sglang/srt/custom_op.py,sha256=
|
33
|
+
sglang/srt/conversation.py,sha256=fFP6RxkRolz-YLl55o0juzp0Ov-78j89RCt7Cflzr2Q,38335
|
34
|
+
sglang/srt/custom_op.py,sha256=87r2PIgiGLREsIZQ8qsUD-zgI66_54y9GrE0buXzoCI,3076
|
36
35
|
sglang/srt/debug_utils.py,sha256=slaFOY4BYDBFatkfu8FZlzai-u4LFS-5GUzdr-t50zE,2241
|
37
|
-
sglang/srt/hf_transformers_utils.py,sha256=
|
36
|
+
sglang/srt/hf_transformers_utils.py,sha256=1Ku6POAyk1Hb4Q1VcHTE_2EjujVhPerPO9V9NAcHbOI,11997
|
38
37
|
sglang/srt/jinja_template_utils.py,sha256=Jc6Vl-lYtUyMBSWWQGIMpJQ1O-ceU9c8DbOi_bN-oVk,6719
|
39
|
-
sglang/srt/mm_utils.py,sha256=7o4w1W0VAWgEquVIz7qw7-IxYbZY2g3MrXw9php90oY,12621
|
40
38
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
41
39
|
sglang/srt/operations.py,sha256=ddQ8KO63L73OciaR8MZ9h2h83gKVY4-WuWgeEGowPJA,5346
|
42
|
-
sglang/srt/operations_strategy.py,sha256=
|
40
|
+
sglang/srt/operations_strategy.py,sha256=Pwd2sKeRtKh9WJXgzlNr2tU9y6YMcI3MDLbatHqlMws,7145
|
43
41
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
44
|
-
sglang/srt/reasoning_parser.py,sha256=
|
45
|
-
sglang/srt/server_args.py,sha256=
|
42
|
+
sglang/srt/reasoning_parser.py,sha256=DkZrFhkJ9qe7w46fTnM9sqhXwTDgZxD4qPdGka-Dly8,7579
|
43
|
+
sglang/srt/server_args.py,sha256=Fg1CqO92iiKA5jLd9vqKZ59uwnw0l23DO6KL47kBJgY,75458
|
46
44
|
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
47
|
-
sglang/srt/two_batch_overlap.py,sha256=
|
48
|
-
sglang/srt/utils.py,sha256=
|
49
|
-
sglang/srt/warmup.py,sha256=
|
45
|
+
sglang/srt/two_batch_overlap.py,sha256=kunhMhCF_ucK4EkthOUEUegd1C9j4aSbpBLYaIKYgas,28447
|
46
|
+
sglang/srt/utils.py,sha256=pI-0YtHmQrC2B2Q_uK13qvje1y_ni6TNzqs8W7T3hts,85846
|
47
|
+
sglang/srt/warmup.py,sha256=zldxhMlXpclRAJXmfBjJNUJd1eDizVdysibBvQyTVuA,1782
|
50
48
|
sglang/srt/configs/__init__.py,sha256=8EcVRP95epZ49DxBa6LgKWt7eO3Qe7Hrr3V1c6HkMnY,553
|
51
49
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
52
50
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
53
51
|
sglang/srt/configs/deepseekvl2.py,sha256=X8Q2gm7og_Ylx6tbFXetusfIJIXjWY_YH_p90C67BTI,23397
|
54
52
|
sglang/srt/configs/device_config.py,sha256=kdwFrk5myAURxdp4rSr8ANpBpSJfuBDoT-kuCyuscRs,442
|
55
53
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
56
|
-
sglang/srt/configs/internvl.py,sha256=
|
57
|
-
sglang/srt/configs/janus_pro.py,sha256=
|
54
|
+
sglang/srt/configs/internvl.py,sha256=Z2kmT-5BzR4EdoLmbsgnK5HBXmpjzKAcaTuHaPYrQHE,27553
|
55
|
+
sglang/srt/configs/janus_pro.py,sha256=95qLFQ43n-q5MVEDnh9OBXCUNXOCofwBKYvd7LKPvRI,19097
|
58
56
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
59
57
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
60
58
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
61
|
-
sglang/srt/configs/model_config.py,sha256=
|
59
|
+
sglang/srt/configs/model_config.py,sha256=EzF91fOMu97BxPFSrVU4r-RTuUS3pqoDObKAstnPxGE,26983
|
60
|
+
sglang/srt/configs/update_config.py,sha256=2EpDVocEpMv35g1V-iPLSaLjBgylC5vN0yYSlW49k5w,4664
|
62
61
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
63
62
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
64
63
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -75,28 +74,28 @@ sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCX
|
|
75
74
|
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
76
75
|
sglang/srt/constrained/xgrammar_backend.py,sha256=u9Ao-XX22UzALkATEAR_-0EoyBTxMTJV590qd9LAUHM,7906
|
77
76
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
78
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
77
|
+
sglang/srt/disaggregation/decode.py,sha256=sND6tJTIgxdaqDOem9mAaaMQWZTVxho5sniMOYVkQ7I,33944
|
79
78
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=8UdNaj8KKMLV5Cydhw8gnHM-zRrnKM_AAd3Qc-SRfWg,5648
|
80
79
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
81
80
|
sglang/srt/disaggregation/launch_lb.py,sha256=mcbAztN4gnHevw_T5R2_nWsymsDEY9vHkm7OJ1vr6cc,4211
|
82
81
|
sglang/srt/disaggregation/mini_lb.py,sha256=BBeIdeZZxi7Ra5_hukHHX3TNdyfZ4tP1GBUxC-qrv_g,14401
|
83
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
84
|
-
sglang/srt/disaggregation/utils.py,sha256=
|
82
|
+
sglang/srt/disaggregation/prefill.py,sha256=3u6WCrjogZSqd6yWdBZe1HO4lf6w2e9M7sQtGHyax-Y,23512
|
83
|
+
sglang/srt/disaggregation/utils.py,sha256=pKy2MDWqnfHmktc7bJg0hi_x92ellCtfWB-RJSg1jSw,11343
|
85
84
|
sglang/srt/disaggregation/base/__init__.py,sha256=4VwUv0aWxwmVL1049XK82aLTNxmt0WY5RPy9li-wyVk,160
|
86
|
-
sglang/srt/disaggregation/base/conn.py,sha256=
|
85
|
+
sglang/srt/disaggregation/base/conn.py,sha256=CPDAoAkYaFtVPLa1QROfwipSVe7MH6omzIBHzo8TSYk,2811
|
87
86
|
sglang/srt/disaggregation/common/__init__.py,sha256=7yl-EGLMVKRpBUaGF_7lwAsw2J_mqpRZV0238VGxD9o,126
|
88
87
|
sglang/srt/disaggregation/common/conn.py,sha256=CZR1lMCE_mpSkvjc6BBmSr1SbHY1uZuxjpanazD-YXc,16071
|
89
88
|
sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeKVPMWPcB5ywbE,1194
|
90
89
|
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
91
90
|
sglang/srt/disaggregation/fake/conn.py,sha256=oD1DArn1yDFZCu-X6p93uSLlAXEkt9lYxERICMznxGw,2286
|
92
91
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
93
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
94
|
-
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=
|
92
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=MATJkiS_5Vh8fc8Gx6S6cI3zCYDbgKXVEAa1xkUsCKA,58879
|
93
|
+
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=JYB9T-EPdJNfv4I_sVpmMOZCOJ14itD97ws6tTvj240,4281
|
95
94
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
96
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
95
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=cXqWU2Gbi6E2LS0MznEcgFCrwONhYxBtD-zE9DU32z0,20333
|
97
96
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
98
97
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
99
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
98
|
+
sglang/srt/distributed/parallel_state.py,sha256=tZL5PLVowAQvq5xlT573Di63hWKsiqJZbl-auj85wNA,54997
|
100
99
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
101
100
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
102
101
|
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=qje-PQ3v8yaV-oYVLPws1mgIlXVsGKFCOvXHmSe8ZXg,19624
|
@@ -108,22 +107,31 @@ sglang/srt/distributed/device_communicators/pynccl.py,sha256=obXyCaZznZHSt486XCn
|
|
108
107
|
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6EMz-oPS9J16WHo2Q_SRL1DtlJKK63Hfg,15349
|
109
108
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=d8mykYmXM1lfbPm8GNtqCF0Un_pdXYjbNmsgoVFyyow,20874
|
110
109
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
111
|
-
sglang/srt/entrypoints/EngineBase.py,sha256=
|
112
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
113
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
110
|
+
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
111
|
+
sglang/srt/entrypoints/engine.py,sha256=o6sccP-gdeO6rOY9vbSqVmUNlBrK2YsinrDf42URg5A,31328
|
112
|
+
sglang/srt/entrypoints/http_server.py,sha256=7q6TK02vkppIrW_oa_Xxhr-EV3SNaAwAt_pcnLNfC8w,37503
|
114
113
|
sglang/srt/entrypoints/http_server_engine.py,sha256=ncN45ti9mawSOimPSedI6zugfoMhMQOYh4tmdfC9LcE,4936
|
115
114
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
116
|
-
sglang/srt/entrypoints/openai/protocol.py,sha256=
|
115
|
+
sglang/srt/entrypoints/openai/protocol.py,sha256=qIwhokAlAVbp7Nin1eE4TCnUyrAhKcPS47kzHkhzZg4,18799
|
117
116
|
sglang/srt/entrypoints/openai/serving_base.py,sha256=5NJ2S_6B2NFSwn4nLp6eaeJ5iC3IcQzMEY9lW_gPcdA,5246
|
118
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
119
|
-
sglang/srt/entrypoints/openai/serving_completions.py,sha256=
|
120
|
-
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=
|
117
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=tWKWjspTpNnuk-Aqfl_S6OmpZe6gz5XxmSGEwfIvCsY,35935
|
118
|
+
sglang/srt/entrypoints/openai/serving_completions.py,sha256=emIutVmnJgOgGRuAqdB80-kVHUfQbE67n1VS-76o4QY,16690
|
119
|
+
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=hqPt2ELpT1yQ8sBXo801aLJ3sExoPXs_K5ZQtC2vpAs,6274
|
121
120
|
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=8n6y5kC6UhRpWrDtzH0eIp0dznW12FT60MLCR4bvD2U,3333
|
122
121
|
sglang/srt/entrypoints/openai/serving_score.py,sha256=ebAts-m6Pq-LTgFKwggkywBUrAgUSppHHVEzgwYHUzo,1955
|
123
122
|
sglang/srt/entrypoints/openai/usage_processor.py,sha256=9LTB5rqdRuMKyZrIXiUBuF_WKaSg9X45YdzERDxbtCY,2746
|
124
123
|
sglang/srt/entrypoints/openai/utils.py,sha256=DT9quW0F1DX1P9NAuMxpERgXcNYKKtm7rd7J1m7EaDQ,2112
|
125
|
-
sglang/srt/
|
126
|
-
sglang/srt/
|
124
|
+
sglang/srt/eplb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
125
|
+
sglang/srt/eplb/eplb_manager.py,sha256=Wt7w4L5g1BSsXx1mqoGo8WjkB55f4nGB4KqC3y_ijl8,3394
|
126
|
+
sglang/srt/eplb/expert_distribution.py,sha256=N2wcIzQo9nzPpH5jR63RH7iB00XvH4R8OGp-rR_07f4,31332
|
127
|
+
sglang/srt/eplb/expert_location.py,sha256=unthN8w37bvxf_4Z1xNi-Gi4SGnZbTBbMpHC1be9QMI,16665
|
128
|
+
sglang/srt/eplb/expert_location_dispatch.py,sha256=epq06lcViQXoSL9SIf2urjBDjMTlzql5GwMVFpcOAtI,4144
|
129
|
+
sglang/srt/eplb/expert_location_updater.py,sha256=oVIUYzji6BFEd2AgeRcM6kwEqLwwD3_PEEv3EyWIydk,21100
|
130
|
+
sglang/srt/eplb/eplb_algorithms/__init__.py,sha256=c6fo4qM8N0p5DyyfGp9fxqc2wkxvzSJBzJFRG1I1leg,1959
|
131
|
+
sglang/srt/eplb/eplb_algorithms/deepseek.py,sha256=mMZT7zAAArccdRS0xXxifvMb3qn9enSt426uUTKeiq4,8340
|
132
|
+
sglang/srt/eplb/eplb_algorithms/deepseek_vec.py,sha256=Vzy5Iarua1VgVHzjBNZaVV_vt1LY1BLtJz7PmzB701k,10654
|
133
|
+
sglang/srt/eplb/eplb_simulator/__init__.py,sha256=HIZaXqsvsOCMMJ81dSs1afSGZ5G6OiOZEtHpltyzzjY,21
|
134
|
+
sglang/srt/eplb/eplb_simulator/reader.py,sha256=OlsWqsuXqVQY7PfvvrP-vsl2Ww2Kg4vD_K9BltM_QHo,1828
|
127
135
|
sglang/srt/function_call/base_format_detector.py,sha256=eMSqbx99YPm2m_ChLafFRuLOzXBtA0oJn_Q4FtB3FnM,12950
|
128
136
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
129
137
|
sglang/srt/function_call/deepseekv3_detector.py,sha256=XudIiIt2Mejokg6qOkX7vYS-3XIFstOBHv-m-Q5fBLQ,8970
|
@@ -134,33 +142,36 @@ sglang/srt/function_call/mistral_detector.py,sha256=xNuVl2vDXVYbXyiXLkJZ9VM6njcw
|
|
134
142
|
sglang/srt/function_call/pythonic_detector.py,sha256=rtXSflE4w993a4OqphWG-WQzvwRz0v3dfgHOnte1fpI,8731
|
135
143
|
sglang/srt/function_call/qwen25_detector.py,sha256=9JfZem_5nw91Og2biwq8eIpUQjy_3kFz4TQI8Lc3Vow,4882
|
136
144
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
137
|
-
sglang/srt/layers/activation.py,sha256=
|
138
|
-
sglang/srt/layers/
|
139
|
-
sglang/srt/layers/
|
140
|
-
sglang/srt/layers/
|
141
|
-
sglang/srt/layers/
|
142
|
-
sglang/srt/layers/
|
143
|
-
sglang/srt/layers/
|
145
|
+
sglang/srt/layers/activation.py,sha256=UDrJcnQoIOJjMzZ9XAy5JlEJ-do44tGMtcitY7I8kPQ,7327
|
146
|
+
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
147
|
+
sglang/srt/layers/communicator.py,sha256=_aq6rDgDlRRVXO1EquSNtmMADuQJGdRZkbt0vCxTxqo,19314
|
148
|
+
sglang/srt/layers/dp_attention.py,sha256=V7m_PfvHHtRMJMviIqmoyqf5VFFJLYYcynDuI5dXtAU,10275
|
149
|
+
sglang/srt/layers/elementwise.py,sha256=MyQUflyKEfPZ-BggW1Kd4hB53RFD6FXGc2S5LXjx_do,16026
|
150
|
+
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=IwI3VPHVZaWTgf_rsSH_5QROTcmoWnjlZ9annh7cYRs,5888
|
151
|
+
sglang/srt/layers/layernorm.py,sha256=4KGaB4QSO5hBcr26TtPfspD3XZwr5X55Pkn5xN9eJrQ,8647
|
152
|
+
sglang/srt/layers/linear.py,sha256=cxth3pvLGdud-ZoHrGFhrPeuhLnBX4IWohyBr2gCCv0,54890
|
153
|
+
sglang/srt/layers/logits_processor.py,sha256=tOPMYopEQuoLBzwbjSmU9OWFYh2mmy3ViJSbA_wpFOU,25619
|
144
154
|
sglang/srt/layers/multimodal.py,sha256=YVR69WW-2aGDcZHT8IVJ6F_LRM7wraZr8VjrPDXqDmA,2104
|
145
|
-
sglang/srt/layers/parameter.py,sha256=
|
155
|
+
sglang/srt/layers/parameter.py,sha256=hu1l8Yzd38xQfkRaIOE1ouzxjG6Ro84pt6SfoUB61qU,16936
|
146
156
|
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
147
157
|
sglang/srt/layers/radix_attention.py,sha256=IlqRB4bk06FOH05_7zB8lik0xLpys7jFooLeCwdO0j8,3437
|
148
|
-
sglang/srt/layers/rotary_embedding.py,sha256=
|
158
|
+
sglang/srt/layers/rotary_embedding.py,sha256=EhxI0E8jcTWZ2COpnku7crbW8Hew5fe_ujMndj7hKvE,52246
|
149
159
|
sglang/srt/layers/sampler.py,sha256=xNds1migup2s6b9_pS6ljkJUkvNtv7nmTGeIdOzoQ6w,11182
|
150
160
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
151
161
|
sglang/srt/layers/utils.py,sha256=IWGg1Hb7c33Z3LHRPVJyUAzp3BnSid23ZWXAmJ_Jvp8,1204
|
152
|
-
sglang/srt/layers/vocab_parallel_embedding.py,sha256=
|
162
|
+
sglang/srt/layers/vocab_parallel_embedding.py,sha256=1Av2YHpx-Oa18-33ps0lpkOuUgnY-Y--Yt_I7YcpYBU,23438
|
153
163
|
sglang/srt/layers/attention/aiter_backend.py,sha256=7sEUgViw-xl3yok91yyOD9gTi8lQmME0g0ZiKVTCcyI,32851
|
164
|
+
sglang/srt/layers/attention/ascend_backend.py,sha256=jPCsU9_gH1iZNoZHD9nCeDdVdXqBt31LI65N55BTJPg,8250
|
154
165
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=KXVcCguwXh-PSrY9Y2aUrlXXUhWdbVxqVEF2_xIMvm4,3466
|
155
166
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=SIR7sKCCegwzahSz82I3gsDyN5TkKoa4yG4-pBQWBi4,9813
|
156
167
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
157
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
168
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=ovi2rduqany6oalDWI7WAetjyHO5DybKA3epHimm86o,94076
|
158
169
|
sglang/srt/layers/attention/flashinfer_backend.py,sha256=Ug4SkZnuHjBBwPOj2TfLlg0eU_GoZvKjhY4oYRU_qqU,49666
|
159
170
|
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=NirRlNFxD0S2EncvvmrerIxNfuTnYpvemZV3MR5_FnU,34040
|
160
171
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=5iSic5ho-lkXNas9mR3uLbXbEl-do31gc8gjR7-a79k,20711
|
161
172
|
sglang/srt/layers/attention/intel_amx_backend.py,sha256=hH9lxXs_o66_IVs58oPhRCOXGUrHbXSz82FKtHr9GO8,4092
|
162
173
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
163
|
-
sglang/srt/layers/attention/tbo_backend.py,sha256=
|
174
|
+
sglang/srt/layers/attention/tbo_backend.py,sha256=CBnSDUmDvT-Tbhi9NHNo1LLkgUAcIsWMJgKa-sAIKW8,9318
|
164
175
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=RsI4lYiQJAj-Xy0vKkzbyKOWHAVPOD9b0n0dEehwlos,9496
|
165
176
|
sglang/srt/layers/attention/triton_backend.py,sha256=AryrPc4kzioxkiucPkApMA__0HoQTKOHNpwN0GEgm98,36923
|
166
177
|
sglang/srt/layers/attention/utils.py,sha256=KiRSIHaGBhErUhPWCSD3Uiaqb0pSEF0NJFwTTQXoMks,2887
|
@@ -173,16 +184,16 @@ sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTg
|
|
173
184
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
174
185
|
sglang/srt/layers/moe/cutlass_moe.py,sha256=--bNTA2BGbHeULb_XXDoRUyWWbE-doHo5K5k1T0N0WA,14323
|
175
186
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
176
|
-
sglang/srt/layers/moe/fused_moe_native.py,sha256=
|
177
|
-
sglang/srt/layers/moe/router.py,sha256=
|
178
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
187
|
+
sglang/srt/layers/moe/fused_moe_native.py,sha256=bW3KWxxz9rxKMUQqfmAtF-7ptTODA1pwLydE05ABDJE,5030
|
188
|
+
sglang/srt/layers/moe/router.py,sha256=UrPieRvemN7Ew48gtG7DA2xhNDBRSnZxzugTEBI-0_E,12006
|
189
|
+
sglang/srt/layers/moe/topk.py,sha256=DhG8EIqyhn41erCKRwX2wGrYOOF-1VdBrCZwyyc1Ks0,18048
|
179
190
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
180
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
181
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
182
|
-
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=
|
191
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=bHn50WQ9K57wLxLWZ8ytNJrCi7bAQ6MegN2o7qxB_Mc,40690
|
192
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=DjUSrRAiRzvuDRvF3JyTqupL3z7smzwXO9hQpQOK0Io,56658
|
193
|
+
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=aiBE3mjvWV3eBrFGH9J44tuJncQwOjRS_XeyBNCEtqM,24379
|
183
194
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
|
184
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
185
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
195
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=GQk0WVdPYI1lOsa0ItkiYcGHS_k8r5y7Mfy485MBZl8,63177
|
196
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=wsNUtzqE2Emi0RAwVzpFHUOVOqUMXr3pCMSJHqkc7EE,34126
|
186
197
|
"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
|
187
198
|
"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
|
188
199
|
"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
|
@@ -349,26 +360,27 @@ sglang/srt/layers/quantization/__init__.py,sha256=isMl8LINJFMzEse4r2Ta_7JXT15eKC
|
|
349
360
|
sglang/srt/layers/quantization/awq.py,sha256=KemDG55U3B6YZVjMV71awVAIj0islFvtxcUHmOBeGy0,6739
|
350
361
|
sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
|
351
362
|
sglang/srt/layers/quantization/blockwise_int8.py,sha256=vWyPZsRLhdKtSmjvlT5fsowBK_nEebYbDAUh2yqseGw,15285
|
352
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
353
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=
|
354
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=
|
355
|
-
sglang/srt/layers/quantization/gptq.py,sha256=
|
363
|
+
sglang/srt/layers/quantization/fp8.py,sha256=fPzEIAYqiSgVjVTu6_CceyW-kemzSRGS_Q-FZ0eGAD0,46375
|
364
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=vziHnk-gVbeY3z94216UDCU5kyev36ZrKldMgglSmpw,34718
|
365
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=fsX1x17RwcK88N1WpF-YELQOpkpHvJnoLriZj27H2R8,25611
|
366
|
+
sglang/srt/layers/quantization/gptq.py,sha256=B0J14a-OANM2uglnatukFMlvpDnUprV3-p_l4308WUQ,26838
|
356
367
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
357
368
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
358
369
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
359
370
|
sglang/srt/layers/quantization/modelopt_quant.py,sha256=wW90ZS1ZrGOXf7l5svudmXqAi3JE2SkCV-fwqWeYfdg,30905
|
360
|
-
sglang/srt/layers/quantization/moe_wna16.py,sha256=
|
371
|
+
sglang/srt/layers/quantization/moe_wna16.py,sha256=9w3TYF1aQ0N0zNBgcuyOX-z-zfq4it2ul_MjKk_fPCA,19680
|
361
372
|
sglang/srt/layers/quantization/qoq.py,sha256=adhsCixRUTh1m8sfpRWNhh5oX3I1WJli3Elg8uexP6A,8222
|
373
|
+
sglang/srt/layers/quantization/quant_utils.py,sha256=kBibCBK9DCambuPy2atB82Bmalb-Vs_wbQoVHT7h2Lw,5089
|
362
374
|
sglang/srt/layers/quantization/utils.py,sha256=qHdWbLQD8teKhv2tOcuyGegpFonXygoJHwCAD7Ur5MA,5439
|
363
375
|
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=ZB6ydquyPOORDe9OCoEBRH6dsQhCeRWv1YIgm8UDQwQ,11622
|
364
|
-
sglang/srt/layers/quantization/w8a8_int8.py,sha256=
|
376
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=aPMm-sk5nBpHwHzkedvuAWXiqWpp_NPyVaPHxHnuhVg,10847
|
365
377
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
366
378
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=EaOKuIA0zXwqmH_eVhWeNdGJT9d1d9gVvFyYkgpdjDg,25665
|
367
379
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=w19mhCnOre3j6L2-Tc_sRtBPgwBOAKV4QmYLpzyU_Fk,26637
|
368
380
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
369
381
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
370
382
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
371
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256
|
383
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=VvqVpAr66AlS5IPVuIR5Nu0ESH0oAoKo545jNart6lI,5493
|
372
384
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=SkeQYXW5i6M3ZLp867KFwQXVBcIPAcdYFILUTY0A850,5934
|
373
385
|
"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
|
374
386
|
"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
|
@@ -527,9 +539,9 @@ sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=BrzCCxX
|
|
527
539
|
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=zkMzBAqQTSwG9TlGPuwmHV1yN0v5Y_5Hgyo0CKQDVNU,741
|
528
540
|
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=On_uvP1ThxgQFAzOWKoteM0vIOHqmtI127A4qbPtmbc,3264
|
529
541
|
sglang/srt/lora/layers.py,sha256=FaTYf0w3zbKKKAT1nJdAzGRtxvySB6FpNKXvEi5RHH0,12958
|
530
|
-
sglang/srt/lora/lora.py,sha256=
|
542
|
+
sglang/srt/lora/lora.py,sha256=v4mkNOypfPXLW1mv_uKj2M-kR-CnzSmu0GReKafGSrc,9667
|
531
543
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
532
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
544
|
+
sglang/srt/lora/lora_manager.py,sha256=sdfSP0o3u4sMlzaVO1N7xhprfydFG-VSutmtOFlu-cE,20060
|
533
545
|
sglang/srt/lora/mem_pool.py,sha256=M4l4RO4tRjii5T4fq89nUoKJNHusaQHwvLrkryBCb1U,10132
|
534
546
|
sglang/srt/lora/utils.py,sha256=f3eySsA2tqlzMkvqwtRPWKIRjDiMk6ZFh9CJfUYdeqI,5486
|
535
547
|
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
@@ -541,63 +553,41 @@ sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=qCpJAksCSXS3Znm-ABx1QfrdNqj9hrP6
|
|
541
553
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=yNBgl8jS76DPlGJg8puRkSnKkewf2_2oKfVZZRq4lYY,4351
|
542
554
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=EoF9HymgQ1V9DwyOJOvbw1hCbEjprVOne_fC4VHgj-s,4518
|
543
555
|
sglang/srt/managers/cache_controller.py,sha256=K00t5dSZU6gbAMHZWhNyj0ndgHISvelTl7UMI5KqBuE,19352
|
544
|
-
sglang/srt/managers/configure_logging.py,sha256=
|
556
|
+
sglang/srt/managers/configure_logging.py,sha256=8sNXZ2z9pBWOwn-X3wyz013Ob8Nbm1zDxRkxoZjH-l4,1633
|
545
557
|
sglang/srt/managers/data_parallel_controller.py,sha256=PZ-wOcAFn3PQqMB6I2vjIsFmplf0nlNl5hqTDKTHTG8,12112
|
546
558
|
sglang/srt/managers/detokenizer_manager.py,sha256=SpLxTsSPKBZfD-ZMhJ5zpPPGuUb8PmcYgFSL9CsurU4,10696
|
547
|
-
sglang/srt/managers/
|
548
|
-
sglang/srt/managers/
|
549
|
-
sglang/srt/managers/
|
550
|
-
sglang/srt/managers/
|
551
|
-
sglang/srt/managers/io_struct.py,sha256=bWybydmTbTuKW_AO6VjHPhB5jbWFdA7qcxb5Ee7Txkg,33687
|
552
|
-
sglang/srt/managers/mm_utils.py,sha256=mA9W4xZBnXfs-4ZeALvhdpGAYxrJGfOxBWyoHVrt44Q,26518
|
553
|
-
sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
|
554
|
-
sglang/srt/managers/schedule_batch.py,sha256=meRGsHztVoSWNHuyq-Qzb_0Xk88d4OasGTvTYBvKoI8,72781
|
559
|
+
sglang/srt/managers/io_struct.py,sha256=DQ2zg8InwXHgOa06n47rbwTzR5mYkj4OGQe5rZ0T77k,35137
|
560
|
+
sglang/srt/managers/mm_utils.py,sha256=px_pMotzBLhuqw-mLXXzf8N1DthhDn9ILsIVIzW9y74,26582
|
561
|
+
sglang/srt/managers/multimodal_processor.py,sha256=mzCrN-8H0bE0iMO8UzxmYmhE2M1qsbVJXGdhAYcjjYA,2016
|
562
|
+
sglang/srt/managers/schedule_batch.py,sha256=3NF590tt4TJ99svwdrlsrFiICH_8X2DpSOj1ebEUSC8,73119
|
555
563
|
sglang/srt/managers/schedule_policy.py,sha256=0T8URzQmLvEmG-42-SFBBl9WnsOSwYO8-_CcBpuD38M,20474
|
556
|
-
sglang/srt/managers/scheduler.py,sha256=
|
557
|
-
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=
|
558
|
-
sglang/srt/managers/session_controller.py,sha256=
|
564
|
+
sglang/srt/managers/scheduler.py,sha256=ZC49CVTsVlDh77QCq5UPhy04NM9FV5YHXuMg4M0cwEE,112191
|
565
|
+
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=XAK2aeLleZBaLtzebEKdpaz9E7uKnHV7ywHSk_WPDYo,30148
|
566
|
+
sglang/srt/managers/session_controller.py,sha256=dzlMNZlo20FTSl64QqK7y7pElsdCy8ICOWWBPTBVwgs,6040
|
559
567
|
sglang/srt/managers/template_manager.py,sha256=RrwRA2oqId_PMQ98qJQGwIxMroOxiorl2sGC9ARou_0,8543
|
560
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
561
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
562
|
-
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=
|
568
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=I2M8Hpj9T120rJYP5Hdu6cV72oPmsoRr829LiT7O4Dk,73655
|
569
|
+
sglang/srt/managers/tp_worker.py,sha256=kyk2EVd3eP0gpgVETJ6J_BdxIDbiB76AfpN4_-Xqkrs,10896
|
570
|
+
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=EFbtichmZjMoBgRa0AMIGdKGur1i8bpd3JvaDi-SsK8,10663
|
563
571
|
sglang/srt/managers/utils.py,sha256=9_VGE48EK0PXVJ26aYvbRJ6n7gIZALvCcf6uZCccCgM,1369
|
564
|
-
sglang/srt/managers/
|
565
|
-
sglang/srt/
|
566
|
-
sglang/srt/managers/eplb_algorithms/deepseek_vec.py,sha256=Vzy5Iarua1VgVHzjBNZaVV_vt1LY1BLtJz7PmzB701k,10654
|
567
|
-
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=DQk5qNh7MDY9DQoASiQbCTwRb2HdvLWobzHmE0Ni_fg,21500
|
568
|
-
sglang/srt/managers/multimodal_processors/clip.py,sha256=lRc2mcuDbAhZVf-0EfkO81pqDiol9zLvTpDqtPIBQ2k,1525
|
569
|
-
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=CMfhhdq7u6GzT8ZENo7ByClvQEx-HKaTGVgdYM1vMNw,3460
|
570
|
-
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=oBHXlbwto_84ZkjkW2A7F3Z7kNuDf039uDH4HVXKE1s,2290
|
571
|
-
sglang/srt/managers/multimodal_processors/internvl.py,sha256=ASv3MQ0Ju6oZG7UceS5ziy4rL2d8Xf1_LbIFmEAuz2E,9512
|
572
|
-
sglang/srt/managers/multimodal_processors/janus_pro.py,sha256=nSZYKLoCZtv7sQIM21KCt4jpnzVfcsF84m9CFPWwR7s,2058
|
573
|
-
sglang/srt/managers/multimodal_processors/kimi_vl.py,sha256=8DER6QFDrmD0sZMjlAffY4z3jtBrrIYoU8ogpZIKNio,1868
|
574
|
-
sglang/srt/managers/multimodal_processors/llava.py,sha256=90D2A09EHgdWwapVSeLg5J4YsioeT2AvGmJkepZA-5I,8100
|
575
|
-
sglang/srt/managers/multimodal_processors/minicpm.py,sha256=y-1UHmXq2bmDtTax2b-rJf-CI478MMpoz9nY3b-OKzI,5561
|
576
|
-
sglang/srt/managers/multimodal_processors/mlama.py,sha256=MLiGS606LzVtdoXvjWGANx-K_7nE9J_fMVmkXN7Gz8k,1661
|
577
|
-
sglang/srt/managers/multimodal_processors/mllama4.py,sha256=IAu09ZPMAHxZKsfGiKjZU_Fruj4AmKA0poqXC0zufWQ,5813
|
578
|
-
sglang/srt/managers/multimodal_processors/phi4mm.py,sha256=-yTlt2kQkrgks2IzaRKmEj-7siAvTDhZHDR_J3NVFdw,2610
|
579
|
-
sglang/srt/managers/multimodal_processors/pixtral.py,sha256=uQJYbxhafNCmg0xP52FdElnkUatAyintER1XNuKz3b8,4195
|
580
|
-
sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=RLv8sBuKhAjeaVqrFR7hwEEw7fX1WOMZ6r2R4gFeV04,7025
|
581
|
-
sglang/srt/managers/multimodal_processors/vila.py,sha256=AeQlhdIKKoN0lre8_zYQ7YpGu7I_rux1bRLt70sPKJ0,2594
|
582
|
-
sglang/srt/mem_cache/allocator.py,sha256=gujYY5DFYQIz8VDAUOjATKtxUMpdRo6xkBunPF08SG4,12526
|
572
|
+
sglang/srt/managers/multimodal_processors/qwen_audio.py,sha256=vUkXsa_Ipe_EjWPWDSSUrbm8v-fDenEy3w3fpHwaf2g,3170
|
573
|
+
sglang/srt/mem_cache/allocator.py,sha256=MJUPQt4ECj4ReGeUVGVUNfwrwjHBbf3youdkyp3jCGQ,21633
|
583
574
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=XHSzXKgBin-m1HsL47K-GobhLnajaGxqLqGtrLsWaZ0,2540
|
584
|
-
sglang/srt/mem_cache/chunk_cache.py,sha256=
|
575
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=MWo4DwRkHKOLKyow53YrGQdvn2dI7hVJuf2Gf-SPAr0,3110
|
585
576
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
586
577
|
sglang/srt/mem_cache/hiradix_cache.py,sha256=Z_XgbLBxI8SN7kgsi1R6iX6AfgDUF5-ynVnBVRF7KUw,17061
|
587
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
578
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=soOE9l5qZlWHFbqIHwSEW4l7NQXzmEjpJKk1rfehQZc,37055
|
588
579
|
sglang/srt/mem_cache/memory_pool_host.py,sha256=9N34Y7P0aM2xkmhsEw2_W8xN897h-HEwzRPIu1REwac,13186
|
589
|
-
sglang/srt/mem_cache/multimodal_cache.py,sha256=
|
580
|
+
sglang/srt/mem_cache/multimodal_cache.py,sha256=wZl2KeEl3xeoEsYdH33UoM-FO8kqfLo_XUgereJVvoM,1348
|
590
581
|
sglang/srt/mem_cache/radix_cache.py,sha256=ojr9_bUwnPocmpbGZXz8JKac4dS-PrfNYk8UqF4Gvi8,17936
|
591
582
|
sglang/srt/metrics/collector.py,sha256=C9QEJDOEdOPBwy2IJwFS3R6VbGzVzGs2xakKCCPvQDk,19903
|
592
583
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
593
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
594
|
-
sglang/srt/model_executor/
|
595
|
-
sglang/srt/model_executor/
|
596
|
-
sglang/srt/model_executor/model_runner.py,sha256=mbYBcddyYxBuRcFmRawa17xdxySxdG-LwxmovH4BCLw,54309
|
584
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=3pc1_TpGmUAI51SxVubGGZIRuBmZrj8kOuch970RN2A,30505
|
585
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=uzWEXYdVJie1xLikH6pmOnT64BDnZvJvfK7gCHH82x4,29572
|
586
|
+
sglang/srt/model_executor/model_runner.py,sha256=kfFWWHMXJ6X9WEQgEj618mx8zIc9qvhXC5-K2ICDPJM,65709
|
597
587
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
598
|
-
sglang/srt/model_loader/loader.py,sha256=
|
588
|
+
sglang/srt/model_loader/loader.py,sha256=oHIX6qiGfXDQWzP6NuPQfc_haFsWykbcVTKEGUwC_t0,59164
|
599
589
|
sglang/srt/model_loader/utils.py,sha256=zSZBPA9ErPmkf-HfCxJjhmiFwYueB15KUg7NFspLvPY,4454
|
600
|
-
sglang/srt/model_loader/weight_utils.py,sha256=
|
590
|
+
sglang/srt/model_loader/weight_utils.py,sha256=dfepjK1lhcFoxX6Vflb3imiHaj9_Tep_uZ7j3lfN9jE,38004
|
601
591
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
602
592
|
sglang/srt/models/bert.py,sha256=ODJe8YfNRP-hHsomFWk4_QpcuiSsNfjzGf256EDS0Pc,15802
|
603
593
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
@@ -606,91 +596,113 @@ sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo
|
|
606
596
|
sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,15598
|
607
597
|
sglang/srt/models/deepseek.py,sha256=ZnN02HdgXCB23Vno5V9UMUoOxH5HC82vNTwsVulUJ-o,17206
|
608
598
|
sglang/srt/models/deepseek_janus_pro.py,sha256=OeeI7vZbE4HGpxa8CwT6-Lbfs7J7WMQ3oBNpVJQpv3w,70450
|
609
|
-
sglang/srt/models/deepseek_nextn.py,sha256=
|
610
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
611
|
-
sglang/srt/models/deepseek_vl2.py,sha256=
|
599
|
+
sglang/srt/models/deepseek_nextn.py,sha256=47fehxRdiOizr0rdLg5f1fzQEx6gGAOcDcWKtblloyk,5928
|
600
|
+
sglang/srt/models/deepseek_v2.py,sha256=L0ewZPnxM6xCCB8tJxswwNKAjE-q_SCloJfZx8Y8LoU,100660
|
601
|
+
sglang/srt/models/deepseek_vl2.py,sha256=F-nf2qRiiZNg9js__rYFEc9fNs_HVEfAi_Mh1jvqwkQ,13095
|
612
602
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
613
603
|
sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
|
614
604
|
sglang/srt/models/gemma2.py,sha256=kqtwdo93GWKm2iBN29RoIRH2ggRm-K_80LM5btgfBLo,16395
|
615
605
|
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
616
|
-
sglang/srt/models/gemma3_causal.py,sha256=
|
606
|
+
sglang/srt/models/gemma3_causal.py,sha256=CJ2g08Ec7IeoObQIiGH0WIEtYOl05SbJ2g_pfJwSyBs,25130
|
617
607
|
sglang/srt/models/gemma3_mm.py,sha256=b9YmkipsfVb5IXVeIVwW_PviXiCkRULhEsqNOvPoDxU,17221
|
608
|
+
sglang/srt/models/gemma3n_audio.py,sha256=isgKfjA5UieYawxU6medL2ssXlzYPqAbagDBnLcemC0,36405
|
609
|
+
sglang/srt/models/gemma3n_causal.py,sha256=kBDlpSWAg6ZDmUPe08Q7sj5CbdVD_0h07zwJw8sKu7I,36335
|
610
|
+
sglang/srt/models/gemma3n_mm.py,sha256=nCCnVbGvkYit6UXljZWRAQagGeSe0Ej9YnH0DbEaN8Q,18689
|
618
611
|
sglang/srt/models/glm4.py,sha256=2VQzUqFkQTy_2nfkxP9SF6_9kKLTZUExGRjge7r99Es,11265
|
619
612
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
620
613
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
621
614
|
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
622
615
|
sglang/srt/models/grok.py,sha256=vESZeGS4adI_JAerXIkCcTm15-CNiGeS7VHc36C6w1A,28033
|
616
|
+
sglang/srt/models/hunyuan.py,sha256=YRx9Zafs8HVTNHxlMMKdbV3ELMn6rWi9GKlk94U_R7E,28990
|
623
617
|
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
624
618
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
625
619
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
626
620
|
sglang/srt/models/internvl.py,sha256=fZ18eKFYvvtYqoBRXKmS7KlgHMewJSAykADnrf0N3nk,23267
|
627
|
-
sglang/srt/models/kimi_vl.py,sha256=
|
621
|
+
sglang/srt/models/kimi_vl.py,sha256=oFmkPGaCW3QcrExie5o0fqnvk73w6K8zVbaRXw0kV3k,12811
|
628
622
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
629
|
-
sglang/srt/models/llama.py,sha256=
|
630
|
-
sglang/srt/models/llama4.py,sha256=
|
623
|
+
sglang/srt/models/llama.py,sha256=xUVXptse-TTTPaZGLPYf8OoL2giczzl9FGiNRjy1CWA,27505
|
624
|
+
sglang/srt/models/llama4.py,sha256=nF19fG2ZdT1bUX3pncckwJ9dRMSazNZx647EW__rBRo,18746
|
631
625
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
632
626
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
633
|
-
sglang/srt/models/llama_eagle3.py,sha256=
|
627
|
+
sglang/srt/models/llama_eagle3.py,sha256=715soylDE3kOMWskbPy_70BFxaSc5ptaHCS1v3-ViA0,8579
|
634
628
|
sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OWYfirZnA,3254
|
635
629
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
636
|
-
sglang/srt/models/llava.py,sha256=
|
630
|
+
sglang/srt/models/llava.py,sha256=r0nHLVRI7AcFEhruqdRXTLWeQ-Cx3uty9wIkHh3TxZs,37507
|
637
631
|
sglang/srt/models/llavavid.py,sha256=q0lHlRnoYHKJZsWnkIQdd6dYAQ26t7XsmrqA0zDGmZc,12829
|
638
632
|
sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
639
633
|
sglang/srt/models/mimo_mtp.py,sha256=jSmqJAXu7G3OO7jW1oa2suI4H_Yl7u5ZT7w4lHFbHhg,7292
|
640
634
|
sglang/srt/models/minicpm.py,sha256=m5HFsSJj0Po09LY9R6qj6K4gceqWDMOePz3NDGgMGT4,14691
|
641
635
|
sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
|
642
|
-
sglang/srt/models/minicpmo.py,sha256=
|
636
|
+
sglang/srt/models/minicpmo.py,sha256=CwcogzxwTRAInBynhP3z_YAFVq4DC_YN3gG_95C6MQ8,76034
|
643
637
|
sglang/srt/models/minicpmv.py,sha256=7YYWwk4LX0Z7lZegnsldctb-a9zGGgJUdjFeGo-oLv4,30426
|
644
|
-
sglang/srt/models/mistral.py,sha256=
|
638
|
+
sglang/srt/models/mistral.py,sha256=Ox07RJpTYl-4Pb25UIghL_66o9TTA6lPmsUyent_Flc,3480
|
645
639
|
sglang/srt/models/mixtral.py,sha256=n-Pz7fyWE4m6Uh7sjzAYKNr5Wy4QUj5Yekl0qiCwQI8,17055
|
646
640
|
sglang/srt/models/mixtral_quant.py,sha256=-kQw9r8KcLdO8SNN9RKXzrGq9Q2Al9l9cWHi1VrZSRM,15260
|
647
641
|
sglang/srt/models/mllama.py,sha256=pkS0UWiqKJHRsFtSZzpSI9O6B5_j1OtI5pf_nyDPp3U,39707
|
648
|
-
sglang/srt/models/mllama4.py,sha256=
|
642
|
+
sglang/srt/models/mllama4.py,sha256=4E7qGicVuTKAs3vHF2SnoNlQP1mm2eBrsLU7QK3x9ow,10519
|
649
643
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
650
644
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
651
645
|
sglang/srt/models/olmoe.py,sha256=TMzt-yB891bvA4X50xL0NjNnFYSx9imlA7N1EG8KNK0,15949
|
652
646
|
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
653
|
-
sglang/srt/models/phi4mm.py,sha256=
|
654
|
-
sglang/srt/models/pixtral.py,sha256=
|
647
|
+
sglang/srt/models/phi4mm.py,sha256=rBGRtTLGBJZGYXhvotBjJbAUpbLxsCZahDtrInP_FGM,19064
|
648
|
+
sglang/srt/models/pixtral.py,sha256=ZkZrV0mEfmbBdgRko2AvsMFZbAVskgp_5a5p1xCSRN0,16835
|
655
649
|
sglang/srt/models/qwen.py,sha256=xYkVmMZS2uMqWhfndc8EYm0olpKFnggfuMp_6aobVi4,10758
|
656
|
-
sglang/srt/models/qwen2.py,sha256=
|
657
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
650
|
+
sglang/srt/models/qwen2.py,sha256=uF71yk7ZbW4ENbfdq7Sf4dWwZjLT2JNLyzkcFtmLEoU,20983
|
651
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=SuJe8YfRQkJJo_bBSgRodY2-hUl_evYdNuAal16jrxs,22563
|
652
|
+
sglang/srt/models/qwen2_audio.py,sha256=linjXOVGhjyKk5DUx9Uw-BJa1N-YcqCFUpsj0Zr_98A,7877
|
658
653
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
659
654
|
sglang/srt/models/qwen2_eagle.py,sha256=6spFg6JYQGeUXLv2Q5eMkVzZvnqGyvW6SdVBtFMxlTM,4806
|
660
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
655
|
+
sglang/srt/models/qwen2_moe.py,sha256=fmVDsb4ju0suMCZiDAhocPxO9gQecOWOxmdf-W1elvg,24239
|
661
656
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
662
|
-
sglang/srt/models/qwen2_vl.py,sha256=
|
663
|
-
sglang/srt/models/qwen3.py,sha256=
|
664
|
-
sglang/srt/models/qwen3_moe.py,sha256=
|
657
|
+
sglang/srt/models/qwen2_vl.py,sha256=Xo7f-ChWZJNJpM0RNe-GsYU4_VXPR62ZNMSXBVYr4QY,20842
|
658
|
+
sglang/srt/models/qwen3.py,sha256=3alBwittpU5m44DnJZ5mjRM0x1UShepu2CREWotPYqA,17777
|
659
|
+
sglang/srt/models/qwen3_moe.py,sha256=qP_UlowZPOOB9sALkRtaK3-gpXlsmgEJMaJ17bycpJ0,32867
|
665
660
|
sglang/srt/models/registry.py,sha256=bH9H0OiNV0Cn7FRBM30Oh6dxICTs9mJscdLtHYPJvxc,3783
|
666
661
|
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
667
662
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
668
663
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
669
664
|
sglang/srt/models/torch_native_llama.py,sha256=oTxxof5Wx2b2egIwWx56LeHjtPGQleQ2zM5jXHMiuOU,19293
|
670
665
|
sglang/srt/models/transformers.py,sha256=_CL0npi-_HvqzxkLgFhv2EE3bfGvCLXPYAtPFywZOr0,10260
|
671
|
-
sglang/srt/models/vila.py,sha256=
|
666
|
+
sglang/srt/models/vila.py,sha256=Q8Z4q8DH3SAiaYocGys6AkEpw8zg3-l3pb5wLcyVves,9780
|
672
667
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
673
668
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
674
669
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
670
|
+
sglang/srt/multimodal/mm_utils.py,sha256=7o4w1W0VAWgEquVIz7qw7-IxYbZY2g3MrXw9php90oY,12621
|
671
|
+
sglang/srt/multimodal/processors/base_processor.py,sha256=05moS0iDYUfI9CKzio5ip8cjsfUjqYi_S5fzArWJxw8,21539
|
672
|
+
sglang/srt/multimodal/processors/clip.py,sha256=chKReTXD4ETUQ0s7BOk_AmWHEZXR5no6fprrnHwSNIM,1271
|
673
|
+
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=VHrUbOTF_18fPYaEx_awS1UMhOy0nhTXoA17wakwyQ4,3281
|
674
|
+
sglang/srt/multimodal/processors/gemma3.py,sha256=11tIvfpUAc9E_dkZZ-5kupUCn2TJ9e-yBriCpF38Ino,2084
|
675
|
+
sglang/srt/multimodal/processors/gemma3n.py,sha256=FzwkaEhk4ATn4nV9zkGdBgcHTTTVK5CbnTx_vBr0QxI,3116
|
676
|
+
sglang/srt/multimodal/processors/internvl.py,sha256=ffLizY9v3jYIm026UZg6MHBNadyUWYgag8HbL3hFtis,9334
|
677
|
+
sglang/srt/multimodal/processors/janus_pro.py,sha256=TOxSQH8gVirAYZvcQ_3Gd2uvNMzzWwubF4ROKDWUO9g,1913
|
678
|
+
sglang/srt/multimodal/processors/kimi_vl.py,sha256=2KMB6iEXizHXzE6yjtzS7V1RFhsA2hhuxk3Bx0ySMDM,1653
|
679
|
+
sglang/srt/multimodal/processors/llava.py,sha256=tIjeDPYxvMWUMXXLcfzzuaLPvdBtPrRzM25QzP0cnaE,7962
|
680
|
+
sglang/srt/multimodal/processors/minicpm.py,sha256=9Y8KCo5eCX274CJIx1D8BVWgferjc0Uf6Zd_HR_IMnY,5316
|
681
|
+
sglang/srt/multimodal/processors/mlama.py,sha256=bW0hVPtRMqYz1RR2I19QtZLUTTPzInZv_6ZhVPJBieo,1406
|
682
|
+
sglang/srt/multimodal/processors/mllama4.py,sha256=V2Y3G-bv2wdqkgE_XGPLMJp_nSEEr-MD8_S4h8QTDDk,5752
|
683
|
+
sglang/srt/multimodal/processors/phi4mm.py,sha256=ZYH1fWTpbz6wLGyV6c51kd54vwPRm0qdZiQcc0GlXGI,2337
|
684
|
+
sglang/srt/multimodal/processors/pixtral.py,sha256=VsCIFJpIUM3pSGNe_uRd8NlH7zSokW4xHOrZSi70R1o,4055
|
685
|
+
sglang/srt/multimodal/processors/qwen_vl.py,sha256=lKVWvvtB4OWfyJ9YZLuJapiW93cGb4T3SoqSAsPc1S4,6874
|
686
|
+
sglang/srt/multimodal/processors/vila.py,sha256=cfBY1Lmlndb-aNLpOyAffi7QPCI6rIYCdAnuxfaNcnA,2176
|
675
687
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
676
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
688
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=m8m-mXu3N8hLYFhAkRopePDT5Ozkd4KAmWDgM_9_4iA,14536
|
677
689
|
sglang/srt/sampling/sampling_params.py,sha256=L2cU3MhAo9OvfdEtTdJidp9nTOkD6tiwlegxQ5vgIfU,6127
|
678
690
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
679
691
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
680
692
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
681
693
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
682
694
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
683
|
-
sglang/srt/speculative/build_eagle_tree.py,sha256=
|
695
|
+
sglang/srt/speculative/build_eagle_tree.py,sha256=O9LJNaBflgJdWT94D-rGH1gJFJ18nst2oOD8HnA2mZ4,12859
|
684
696
|
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=fSNaHYJOQUgy2_AHRlZPYSQRIMgSiL_Pz5h53eothx4,14239
|
685
697
|
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=sdIHbcWwgsXDoo64-T5veDuYB5eHC9QBwu2Ns29SCSI,14930
|
686
698
|
sglang/srt/speculative/eagle_utils.py,sha256=cBQYqryCr4is5E_16xIcUue0Q2_Mn4meY8NCyuu4RAg,45558
|
687
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
699
|
+
sglang/srt/speculative/eagle_worker.py,sha256=iOwloJqhYIrgBdnZQz9NV3zuiAe5dXJJa0QeSIg92x8,38180
|
688
700
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
689
701
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
690
702
|
sglang/test/few_shot_gsm8k.py,sha256=qnEejCyPHGEMBEiNc7T4-t9lvoo2DNN72RXw-ei_TnY,4300
|
691
703
|
sglang/test/few_shot_gsm8k_engine.py,sha256=Yf1Dg0Tk-tY4v1oj_UTxJ7950CWn6kRMbQKDjT2Orgo,3902
|
692
704
|
sglang/test/run_eval.py,sha256=K4Z3OdMPvLeuGJhWWTBD0F-MOUFeBYLvsPnDQ44bd18,4036
|
693
|
-
sglang/test/runners.py,sha256=
|
705
|
+
sglang/test/runners.py,sha256=BmIxB7H5N0ib1Tmc88L2gLuRYpat_lkxAewtjA1fjbE,32804
|
694
706
|
sglang/test/send_one.py,sha256=XNZdfZs21tXDBwrDj2pq46WQd5smiKoYETY8U09c1Z8,5079
|
695
707
|
sglang/test/simple_eval_common.py,sha256=OW4Z7O33QqDySRFuHIC4Ouidfup4eaOEuR9i7xJzkDY,12379
|
696
708
|
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
@@ -709,13 +721,13 @@ sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsu
|
|
709
721
|
sglang/test/test_fp4_moe.py,sha256=U4LHzpGl6pCiCZiENRPxVP6hxqkqRZ_0WXbB29vYeAo,8187
|
710
722
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
711
723
|
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
712
|
-
sglang/test/test_utils.py,sha256=
|
724
|
+
sglang/test/test_utils.py,sha256=u3L0E_5Evrv7Wjss_ZMNnro4HwMStQcUvg6cQvL_eBY,36778
|
713
725
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
714
726
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
715
727
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
716
728
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
717
|
-
sglang-0.4.
|
718
|
-
sglang-0.4.
|
719
|
-
sglang-0.4.
|
720
|
-
sglang-0.4.
|
721
|
-
sglang-0.4.
|
729
|
+
sglang-0.4.9.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
730
|
+
sglang-0.4.9.dist-info/METADATA,sha256=tH3lSIOqvezltkU9P2f6oqUauU_5S8qnLr3jYUIRiV0,27125
|
731
|
+
sglang-0.4.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
732
|
+
sglang-0.4.9.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
733
|
+
sglang-0.4.9.dist-info/RECORD,,
|
sglang/math_utils.py
DELETED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|