sglang 0.4.6.post2__py3-none-any.whl → 0.4.6.post3__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 +1 -11
- sglang/bench_serving.py +149 -1
- sglang/lang/chat_template.py +44 -0
- sglang/srt/configs/deepseekvl2.py +3 -0
- sglang/srt/configs/device_config.py +1 -1
- sglang/srt/configs/internvl.py +696 -0
- sglang/srt/configs/janus_pro.py +3 -0
- sglang/srt/configs/model_config.py +17 -0
- sglang/srt/constrained/xgrammar_backend.py +11 -19
- sglang/srt/conversation.py +30 -3
- sglang/srt/disaggregation/decode.py +4 -1
- sglang/srt/disaggregation/mini_lb.py +74 -23
- sglang/srt/disaggregation/mooncake/conn.py +9 -18
- sglang/srt/disaggregation/nixl/conn.py +241 -71
- sglang/srt/disaggregation/utils.py +44 -1
- sglang/srt/distributed/device_communicators/custom_all_reduce.py +1 -8
- sglang/srt/distributed/device_communicators/npu_communicator.py +39 -0
- sglang/srt/distributed/device_communicators/pynccl.py +2 -1
- sglang/srt/distributed/device_communicators/shm_broadcast.py +2 -1
- sglang/srt/distributed/parallel_state.py +22 -1
- sglang/srt/entrypoints/engine.py +14 -2
- sglang/srt/entrypoints/http_server.py +28 -1
- sglang/srt/entrypoints/verl_engine.py +3 -2
- sglang/srt/hf_transformers_utils.py +20 -1
- sglang/srt/layers/attention/flashattention_backend.py +146 -50
- sglang/srt/layers/attention/flashinfer_backend.py +23 -13
- sglang/srt/layers/attention/flashinfer_mla_backend.py +62 -15
- sglang/srt/layers/attention/merge_state.py +46 -0
- sglang/srt/layers/attention/triton_ops/merge_state.py +96 -0
- sglang/srt/layers/attention/vision.py +290 -163
- sglang/srt/layers/moe/ep_moe/kernels.py +342 -7
- sglang/srt/layers/moe/ep_moe/layer.py +120 -1
- sglang/srt/layers/moe/ep_moe/token_dispatcher.py +97 -54
- sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +4 -1
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +2 -4
- sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +2 -1
- sglang/srt/layers/quantization/deep_gemm.py +5 -0
- sglang/srt/layers/quantization/fp8.py +108 -95
- sglang/srt/layers/quantization/fp8_kernel.py +79 -60
- sglang/srt/layers/quantization/fp8_utils.py +71 -23
- sglang/srt/layers/quantization/kv_cache.py +3 -10
- sglang/srt/layers/quantization/utils.py +0 -5
- sglang/srt/layers/quantization/w8a8_fp8.py +8 -10
- sglang/srt/lora/lora_manager.py +10 -13
- sglang/srt/managers/cache_controller.py +115 -119
- sglang/srt/managers/io_struct.py +10 -0
- sglang/srt/managers/multimodal_processors/base_processor.py +5 -0
- sglang/srt/managers/multimodal_processors/internvl.py +232 -0
- sglang/srt/managers/schedule_batch.py +19 -1
- sglang/srt/managers/schedule_policy.py +11 -5
- sglang/srt/managers/scheduler.py +28 -13
- sglang/srt/managers/tokenizer_manager.py +24 -13
- sglang/srt/managers/tp_worker.py +9 -12
- sglang/srt/mem_cache/chunk_cache.py +2 -0
- sglang/srt/mem_cache/memory_pool.py +2 -2
- sglang/srt/model_executor/model_runner.py +44 -33
- sglang/srt/model_loader/loader.py +18 -11
- sglang/srt/models/clip.py +4 -4
- sglang/srt/models/deepseek_janus_pro.py +1 -1
- sglang/srt/models/deepseek_nextn.py +1 -20
- sglang/srt/models/deepseek_v2.py +55 -20
- sglang/srt/models/gemma3_mm.py +1 -1
- sglang/srt/models/internlm2.py +3 -0
- sglang/srt/models/internvl.py +670 -0
- sglang/srt/models/llama.py +1 -1
- sglang/srt/models/llama4.py +53 -7
- sglang/srt/models/minicpmv.py +1 -1
- sglang/srt/models/mllama.py +1 -1
- sglang/srt/models/phi3_small.py +16 -2
- sglang/srt/models/qwen2_5_vl.py +8 -4
- sglang/srt/models/qwen2_vl.py +4 -4
- sglang/srt/models/xiaomi_mimo.py +171 -0
- sglang/srt/openai_api/adapter.py +24 -40
- sglang/srt/openai_api/protocol.py +28 -16
- sglang/srt/reasoning_parser.py +2 -2
- sglang/srt/sampling/sampling_batch_info.py +54 -2
- sglang/srt/sampling/sampling_params.py +2 -0
- sglang/srt/server_args.py +30 -6
- sglang/srt/utils.py +35 -1
- sglang/test/test_block_fp8.py +2 -2
- sglang/test/test_deepep_utils.py +219 -0
- sglang/test/test_utils.py +3 -1
- sglang/version.py +1 -1
- {sglang-0.4.6.post2.dist-info → sglang-0.4.6.post3.dist-info}/METADATA +14 -6
- {sglang-0.4.6.post2.dist-info → sglang-0.4.6.post3.dist-info}/RECORD +90 -80
- {sglang-0.4.6.post2.dist-info → sglang-0.4.6.post3.dist-info}/WHEEL +1 -1
- {sglang-0.4.6.post2.dist-info → sglang-0.4.6.post3.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.6.post2.dist-info → sglang-0.4.6.post3.dist-info}/top_level.txt +0 -0
@@ -1,17 +1,17 @@
|
|
1
1
|
sglang/__init__.py,sha256=T-fZEjKP66Q1q3PB56oREs5U3zf6bL0fNcdIbW8jMhE,1652
|
2
2
|
sglang/api.py,sha256=vHiKBg8wwIdmrpnGclop5BzJ-1Q88emrlrfLwNCHg98,7010
|
3
3
|
sglang/bench_offline_throughput.py,sha256=OQb-AjL4UNymmir02ht43uzgaNsnO_I11nXSowKMqBI,13841
|
4
|
-
sglang/bench_one_batch.py,sha256=
|
4
|
+
sglang/bench_one_batch.py,sha256=EnLkIb3JrnrcENMBi_mF7I1HqMJo7ajxsO_IsFaLMkQ,19216
|
5
5
|
sglang/bench_one_batch_server.py,sha256=8VYNhaQbWGP8TkNVuy_sPjD5FiuVZHamtGRWKwa-Z-Q,5962
|
6
|
-
sglang/bench_serving.py,sha256=
|
6
|
+
sglang/bench_serving.py,sha256=ojEmGh2atqc8iwv371xCNsVc0CyFpKGRmr0Jvcjau0I,62858
|
7
7
|
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
8
8
|
sglang/compile_deep_gemm.py,sha256=Umy3oYFeCn40qHUdwlPVuFXmA24fFYB-fuWApgZnEfw,6211
|
9
9
|
sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
|
10
10
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
11
11
|
sglang/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
12
12
|
sglang/utils.py,sha256=GIcgiRHkZ-gyPxXOdn1qFF41jkg4-YdDxbPc4mzO-qk,16159
|
13
|
-
sglang/version.py,sha256=
|
14
|
-
sglang/lang/chat_template.py,sha256=
|
13
|
+
sglang/version.py,sha256=o3vugdOdxbhKKrJaAjwQWlBdh89DmwewfXahpF5Cgxs,28
|
14
|
+
sglang/lang/chat_template.py,sha256=YZPcCTWpW_OTwOm2IJv-CTlijqjhi4EFKlmJVZnn0hI,21059
|
15
15
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
16
16
|
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
17
17
|
sglang/lang/interpreter.py,sha256=OH1SFCm4rUCPO32MTo8j5V2Z13Jic7_r1GQOP1-aHaw,33234
|
@@ -27,29 +27,30 @@ sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZ
|
|
27
27
|
sglang/srt/_custom_ops.py,sha256=L7NuEaRD_Q6Q54n0NZnLXgWZURbnn8Tkg4NQedE6zgA,3616
|
28
28
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
29
29
|
sglang/srt/code_completion_parser.py,sha256=iYRFBxXBAysHcBnf9IHmmyjVkrqKu_9h6Z0_EEjjTp4,5404
|
30
|
-
sglang/srt/conversation.py,sha256=
|
30
|
+
sglang/srt/conversation.py,sha256=c58QHyh1sxzFk9ERX9tkDk6zXT9h5zX08V_vF8BCmFk,35139
|
31
31
|
sglang/srt/custom_op.py,sha256=J1PUcGaeJJjfAjp06BQsLpUkKyR1zsh9MvDiDlqqJsg,1129
|
32
32
|
sglang/srt/function_call_parser.py,sha256=evwCPbLFjgNiRf-1CcxVFYbF08UVsh0ZGvq_R35TPlw,33379
|
33
|
-
sglang/srt/hf_transformers_utils.py,sha256=
|
33
|
+
sglang/srt/hf_transformers_utils.py,sha256=97J396flSaelvOIn0zO8Ji3bvFWUiL2mhLgxnup-d-M,10054
|
34
34
|
sglang/srt/mm_utils.py,sha256=1ScBunw_x4W8ebM_AcJ62-1T2mfT8NlMJqdAhkF1lb0,12367
|
35
35
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
36
36
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
37
|
-
sglang/srt/reasoning_parser.py,sha256=
|
38
|
-
sglang/srt/server_args.py,sha256=
|
37
|
+
sglang/srt/reasoning_parser.py,sha256=UN9UFulb1KRU34308xt9bYckC7syzq6G95M6sjUquZg,6324
|
38
|
+
sglang/srt/server_args.py,sha256=5zM7vmMuZsDDSPEqF-_ggZZPwGdhWcgwzLKyX3Q5iDU,58086
|
39
39
|
sglang/srt/torch_memory_saver_adapter.py,sha256=HYlgYJ2sgmjs2RSjU2KbCaXijRg3mTDZ0ZcCB5Bt6Ps,2211
|
40
|
-
sglang/srt/utils.py,sha256=
|
40
|
+
sglang/srt/utils.py,sha256=_4G44_vC2Aa8wHknV8poLVC7cQu88VE3tgLyW1n8om8,66491
|
41
41
|
sglang/srt/warmup.py,sha256=FmJiYfjRr3X_eAe7ojQaPoN17LvHpjDmRWRnO-k86AQ,1469
|
42
42
|
sglang/srt/configs/__init__.py,sha256=8EcVRP95epZ49DxBa6LgKWt7eO3Qe7Hrr3V1c6HkMnY,553
|
43
43
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
44
44
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
45
|
-
sglang/srt/configs/deepseekvl2.py,sha256=
|
46
|
-
sglang/srt/configs/device_config.py,sha256=
|
45
|
+
sglang/srt/configs/deepseekvl2.py,sha256=xMm_K8qhj6ckRO-neRQ649mBOXGsyn8iL4ts0_dzfJ4,23397
|
46
|
+
sglang/srt/configs/device_config.py,sha256=kdwFrk5myAURxdp4rSr8ANpBpSJfuBDoT-kuCyuscRs,442
|
47
47
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
48
|
-
sglang/srt/configs/
|
48
|
+
sglang/srt/configs/internvl.py,sha256=0wUu_ExziVaA6bJjJ6VKP1uFJOHlj6fVx6y5wLSqJvw,27722
|
49
|
+
sglang/srt/configs/janus_pro.py,sha256=Rrb7kQsNaUP-TiZrjNk8Lr1momFrql8ScEunnrH0_xM,19086
|
49
50
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
50
51
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
51
52
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
52
|
-
sglang/srt/configs/model_config.py,sha256=
|
53
|
+
sglang/srt/configs/model_config.py,sha256=3Q9YSf6ISu6zbgR6PeMCSA5EPZFjGyCchQCE4HjAg7o,23859
|
53
54
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
54
55
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
55
56
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -64,38 +65,39 @@ sglang/srt/constrained/llguidance_backend.py,sha256=S3Mz6j1k816E0w0VE_iZwwtUa2uU
|
|
64
65
|
sglang/srt/constrained/outlines_backend.py,sha256=XbmkZSJzJnnY7k11uj8Et3StfuOiFwRs3ID4IRYAA4Q,6839
|
65
66
|
sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
|
66
67
|
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=XFxdZqvPofmtCeIMqR10NOyph06HwbdXfiVI8rIoV5s,3646
|
67
|
-
sglang/srt/constrained/xgrammar_backend.py,sha256=
|
68
|
+
sglang/srt/constrained/xgrammar_backend.py,sha256=nyjH5I6d96PdyZFEJgI1IShYU6p_ph7uvp2DLZ3zdpM,6955
|
68
69
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
69
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
70
|
-
sglang/srt/disaggregation/mini_lb.py,sha256=
|
70
|
+
sglang/srt/disaggregation/decode.py,sha256=3XQaSCpckX-FvgpshG4ahImL8d13128B889O-F7OOps,25231
|
71
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=SROT_-_OdZSD3R7ar2g90vL5WX5Ijc-K99zz7ewWD7w,12389
|
71
72
|
sglang/srt/disaggregation/prefill.py,sha256=4wLYQtPMbKWMQvF3mGnvr8ygd9xRLO9zTwLKeM5BIf8,15424
|
72
|
-
sglang/srt/disaggregation/utils.py,sha256=
|
73
|
+
sglang/srt/disaggregation/utils.py,sha256=D4NDKWzFAwrsCxHIaOj_C3UNgDiFUBawK0eFkhEKuxI,4886
|
73
74
|
sglang/srt/disaggregation/base/__init__.py,sha256=KR8xXoRCDAy2U623mfP6ujXu42m1_F9EiudjrKu2I_A,130
|
74
75
|
sglang/srt/disaggregation/base/conn.py,sha256=gpf32bhYXWm_iaYB6WcrDaJ-UoL1ZzPI_xpi5pMhRQo,2443
|
75
76
|
sglang/srt/disaggregation/fake/__init__.py,sha256=zmfeKYXjonRhfFOck1c_mP7Q4cW5G0f1RsTwRivKu0s,47
|
76
77
|
sglang/srt/disaggregation/fake/conn.py,sha256=DKEVBgmzV3CNzZ0-r7rFV4orue2iP_7apEtgn-fcTEA,2552
|
77
78
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=1vacEHmWjf7zgbMPzsXKB08FqNKNCquJdUiDlO41BOk,122
|
78
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
79
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=a1keKV59E1DV1TBPifhgK3mkowCDhIeDSi8qncBS0gQ,27913
|
79
80
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=MxDAB9ZetRF1pFS2LP3FVHPtQ1HjIt_SK3UMaYHZ94o,2604
|
80
81
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=n9HjrRk36WUcZNeetGWOh2pSriLp7GNTq7YYX9K3EtY,85
|
81
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
82
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=e7bzFgu4XoCeuyTEyhvWILe1AGlXsqTzX_W2vaXCstg,30056
|
82
83
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
83
84
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
84
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
85
|
+
sglang/srt/distributed/parallel_state.py,sha256=cCQq94H8A-rO2wZf_bCf1lkwcTVOBrHubM9K1PrzVSY,51560
|
85
86
|
sglang/srt/distributed/utils.py,sha256=U-BSaXYjWwnfG8g-tUfBhjKt5Ug097nyHtu3g3aea_Y,8473
|
86
87
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
87
|
-
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=
|
88
|
+
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=qje-PQ3v8yaV-oYVLPws1mgIlXVsGKFCOvXHmSe8ZXg,19624
|
88
89
|
sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py,sha256=fLoptT_U0lVAqkhEg-ge53CdFSIKQpDRiqHYKwJVEZg,10974
|
89
90
|
sglang/srt/distributed/device_communicators/hpu_communicator.py,sha256=gPjEH1-izoby5uDrfUlzNf21luPT0Ow7pJjhCRKnHy8,1728
|
90
|
-
sglang/srt/distributed/device_communicators/
|
91
|
+
sglang/srt/distributed/device_communicators/npu_communicator.py,sha256=bRXN1Md_4SHQGzQYZa2GrHv2zbIU5vSpkueHiAZL1xQ,1345
|
92
|
+
sglang/srt/distributed/device_communicators/pynccl.py,sha256=obXyCaZznZHSt486XCnEOBNG3Cen7ysuuMuGRlTTl-8,10095
|
91
93
|
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6EMz-oPS9J16WHo2Q_SRL1DtlJKK63Hfg,15349
|
92
|
-
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=
|
94
|
+
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=d8mykYmXM1lfbPm8GNtqCF0Un_pdXYjbNmsgoVFyyow,20874
|
93
95
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
94
96
|
sglang/srt/entrypoints/EngineBase.py,sha256=xoyvp6XAeDLY2_Q2Ng33H-fRhrXHv2ldJJKd-HuDhqE,1870
|
95
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
96
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
97
|
+
sglang/srt/entrypoints/engine.py,sha256=a4fWdSQrP1falTtceTf5wXoy7RTdhPDmfHq35ZdSE00,24064
|
98
|
+
sglang/srt/entrypoints/http_server.py,sha256=5rOQGgWQ8Xq0Mt0khZ2au1IV-iQmpiDh4UKQAZ86QYM,30547
|
97
99
|
sglang/srt/entrypoints/http_server_engine.py,sha256=ihA6y3GXRs28Y9U3SgdQcJQjnw_SVIby7QrVgiafX04,4846
|
98
|
-
sglang/srt/entrypoints/verl_engine.py,sha256=
|
100
|
+
sglang/srt/entrypoints/verl_engine.py,sha256=RYizNetTHzcB8dErX1EW4NsyRNGkFPljYaAf7pVRPdM,7002
|
99
101
|
sglang/srt/layers/activation.py,sha256=oSkdo8B8najXFcVay3Y__CEvgXh87lAIhG0CMp2Ugqs,5954
|
100
102
|
sglang/srt/layers/dp_attention.py,sha256=I5cJnBT996mzjpNRrzcZXGt9j8nrkgD4A4T-BHiHkGM,7649
|
101
103
|
sglang/srt/layers/elementwise.py,sha256=XCrR2i-9dP-H6jQo2zUuquwZrsl_wEQqj5Wxk6WUf7o,13987
|
@@ -113,28 +115,30 @@ sglang/srt/layers/vocab_parallel_embedding.py,sha256=QUxd4sELx6p3dHvEKmccPZ-phdd
|
|
113
115
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=lGujcYJ_CxHJy0Q9L6Phn3ds-nBGMy0OGj3R54R65iQ,3334
|
114
116
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=kCNn5Ub0jCsFjhVhuE-9qK53gu5a9oMStMeT2lcc6CU,9904
|
115
117
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
116
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
117
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
118
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
118
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=iloWukpG30lefbAkXGVIARuy5PUQ6l1awVIeOAS_-18,87867
|
119
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=53TXhmBpU5rs04-4u-yXclwJ5UYg7WJfyLDZJ8nSDOU,47651
|
120
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=4BJy18GHYiNVjcSkvmzxgoSk8nugsLrZuars_m-4oYw,32406
|
119
121
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=wR0bkLz3mj5EfuHEi9fwEP2vtq6xFhsrIijpFb009o4,10340
|
122
|
+
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
120
123
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=K5hUqBgakk2COSQqsaxWs0yEVOHS-7BlOygZTOeI8kE,9444
|
121
124
|
sglang/srt/layers/attention/triton_backend.py,sha256=oEEiUwHbm4rNw5ExbQ2c3n0TwAgkk77yuLFenj9bHOo,26902
|
122
125
|
sglang/srt/layers/attention/utils.py,sha256=rxB4sbNIHDTges78bDbnpd_hUgtyb3e16wUwgI4WmoU,2751
|
123
|
-
sglang/srt/layers/attention/vision.py,sha256=
|
126
|
+
sglang/srt/layers/attention/vision.py,sha256=TOTRWzd5d_9fCR8DOvy_oY-vJ1zl2cVYni5hlZGDens,15355
|
124
127
|
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=DPu_aCPgwPqKWZPEQmp_xA7MPbpV2ip-MEICCB470Ao,19120
|
125
128
|
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=vsDZZ5QGb8-KBzADgKshnVQbsW8zRJF1h5hgdPGW5lU,31124
|
126
129
|
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=m12jEnQkNJguATqvZ57HtMC2hhU4wqdB8xAYdh25BxE,13922
|
130
|
+
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
127
131
|
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
128
132
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
129
133
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=U0qh3udHuJJll3udydqABoXPFz0au9aEj8Lv7OAHYvQ,4655
|
130
134
|
sglang/srt/layers/moe/router.py,sha256=5Aeqoix_AS4uymb665OJE904wVSBkQeFdZP4e7KKPvg,10530
|
131
135
|
sglang/srt/layers/moe/topk.py,sha256=K-VU64nWBV07bu1Okn-uYbhz9gylq-KFNRYn2SFzu28,11129
|
132
136
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
133
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
134
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
135
|
-
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=
|
137
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=9uYEBcxw7DLRy-YEZimvBbY_eWLWJgjWGobWka705sk,33546
|
138
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=_GmykK_yQOIKXlmv1SNkUbM4AVAhxQwwx5mrhCF9LlU,40349
|
139
|
+
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=y-t3qG0GS9r8GLTe6_-5BV43Sp5BPHIoveDlYFGIt7s,22051
|
136
140
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
|
137
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
141
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=O5GTg0RkAdqDDFB99Ux4ku7BDuj5_Lr-vNph1RLbedo,55996
|
138
142
|
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=BMOV76fabrZcoyDmRpRbH11Jc0ogWH2k2QAQwvZIpgI,25084
|
139
143
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
140
144
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JJN0hryyLr5Zv3dSS7C8cPFhAwTT6XxUVnBGMZvV6JA,2752
|
@@ -208,9 +212,11 @@ sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=BMOV76fabrZcoyDmRpRbH11Jc
|
|
208
212
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json",sha256=RUkd9fW9WbajF_fFIzppsE1qyWGR5aRC4Cln-BPdu28,3254
|
209
213
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json",sha256=Sc9xK1wtRUqIzXppbutcq-Y2e9M0DZl2OGVzzB0aQuI,3265
|
210
214
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=7YmtaXKnmX8DdYnUJ7WQFa7xjr2Yun9WIdQNoCf_K28,3255
|
215
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=8gNamin6OqMiQ-LMVe4yQBo9ONioiC4loSWPnKcS1XI,3262
|
211
216
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=3Zt4hbC3yJxWvP0T7K93YAPaUP8fQ1P1Wk0CGqtBga8,3259
|
212
217
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=P8GpVR8fjrX7OFbBBFE4y4MJ4uhgoyUV4NYCm1qhWxk,3266
|
213
218
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=4B0SmzRQ2-PsBJcFe7neM1OKfWpsbiY4x6c6COQNMsQ,3254
|
219
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=XyiOCufhAu5BCMHoW9q4gLSRQEGd22bJnJkw15MqFYg,3267
|
214
220
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=f5HTi_9fWvInEyJp8pFgaVN6A9vxu3_845eSZGN9Ypo,3264
|
215
221
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=Piw4LN6d8QYrUahWsw3XUOtTMD1o3vHPwA94sGI56Gk,3242
|
216
222
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=3T8_rF2PEojhgTMyQ8DscXgJCWWdWfDPj4M434zWcA4,3243
|
@@ -291,27 +297,27 @@ sglang/srt/layers/quantization/__init__.py,sha256=WVaItwaovrn-tZiAK0Wvs5RkV_yXi8
|
|
291
297
|
sglang/srt/layers/quantization/awq.py,sha256=KemDG55U3B6YZVjMV71awVAIj0islFvtxcUHmOBeGy0,6739
|
292
298
|
sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
|
293
299
|
sglang/srt/layers/quantization/blockwise_int8.py,sha256=cu9-JiCZDfMfvB97Kv_-eEG87VX5bRFIllFkzpO_xIg,15122
|
294
|
-
sglang/srt/layers/quantization/deep_gemm.py,sha256=
|
295
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
296
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=
|
297
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=
|
300
|
+
sglang/srt/layers/quantization/deep_gemm.py,sha256=kRQlSowo733jtdY3FCwo6ybed6bzG0qzE36jv2B9JpE,13207
|
301
|
+
sglang/srt/layers/quantization/fp8.py,sha256=rYPGv7bn8WaNTLSVhb8vpmaySwadLQPEHdEYBC24Ieo,40709
|
302
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=qc-95CXESRLw5CxApExNKnwsulxbcFwxC8ynT61gins,32570
|
303
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=VHU7glWyKjAMvR-zXAvZIuqMk6V3fj-rOx9K3xR-LEE,20075
|
298
304
|
sglang/srt/layers/quantization/gptq.py,sha256=gyGMOPXHzozK7pPWSjKgLdFX9h7MCEww7n8FqEVEVac,15364
|
299
305
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=CR-VuTTR4GYluOZTpS5mmEz3hYrsY4GOX-G-h3XAYKc,12163
|
300
306
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
301
|
-
sglang/srt/layers/quantization/kv_cache.py,sha256
|
307
|
+
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
302
308
|
sglang/srt/layers/quantization/modelopt_quant.py,sha256=TpPgtbV7O5r1JY4Wm0np2pReQO6XERIdEDQcV41oTn0,16596
|
303
309
|
sglang/srt/layers/quantization/moe_wna16.py,sha256=KtFr4lIslMA12yx4JjXXPOsa5OHjxXWA6scYCRQnFMQ,19483
|
304
|
-
sglang/srt/layers/quantization/utils.py,sha256=
|
305
|
-
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=
|
310
|
+
sglang/srt/layers/quantization/utils.py,sha256=AXvGD8KRZVVrkRR1Y64fGkz4lkUP-CAjAQdp0LDNXrE,5266
|
311
|
+
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=UFwlch8qEm2J4muM4hMATj06-rf-__lSbBqVr00j1tc,11459
|
306
312
|
sglang/srt/layers/quantization/w8a8_int8.py,sha256=MkvmcxQj3X5AZbx8pgnHYAikc_Xd_jOhJXaxx7255ho,8984
|
307
313
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
308
314
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=EaOKuIA0zXwqmH_eVhWeNdGJT9d1d9gVvFyYkgpdjDg,25665
|
309
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
315
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=cGckgXOZQGMv7VIVQeXYblvHKUFC8hLpQfwNb18rj7E,26191
|
310
316
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
311
317
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
312
318
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
313
319
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=-iq634sU38yWFA-h3w-B4kTALeXMo7uRZQI6CckMZTo,5494
|
314
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=
|
320
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=SkeQYXW5i6M3ZLp867KFwQXVBcIPAcdYFILUTY0A850,5934
|
315
321
|
"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
|
316
322
|
"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
|
317
323
|
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=tkLjwLC_aVXhzuvo-2QHkojXZauPJsf3jNHFn1S7uRA,3244
|
@@ -467,7 +473,7 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
467
473
|
sglang/srt/lora/layers.py,sha256=xdP2Gwlw9PCPZBhujGqO6aBn0eGxpVeIBFUp1LIGCto,13119
|
468
474
|
sglang/srt/lora/lora.py,sha256=uNvbjZ_Wr1SLI9-ElRJA_JKwkibSGroP5Bfpsr9MI-Y,7527
|
469
475
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
470
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
476
|
+
sglang/srt/lora/lora_manager.py,sha256=9MoVn-3PaeczidcDuqGQuRtJqa4yP5LW2HX3t5Fbzps,11527
|
471
477
|
sglang/srt/lora/mem_pool.py,sha256=xUFoHUDJgX9lt2YugD9HUY5tIMnJiazYMZ6LYqSGv-E,9633
|
472
478
|
sglang/srt/lora/utils.py,sha256=GjEBgsGhDhX4NqVqeaciznQ8RotKZmb2c-nw4YMLHxA,5251
|
473
479
|
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
@@ -478,27 +484,28 @@ sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=CDGt7lpu9GjykgMtmwbZ3PEqjTlR
|
|
478
484
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=HTfU3HxxxVyaG_aJrrVjPJTnqf62yvepcKJKYkG0XJQ,5944
|
479
485
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=ZmWEqHJaorRNNj-c_ZXPi_pX8X_yIAwudRHAJVa0m08,4350
|
480
486
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=Q58UzWUb3QFqY_ZxWA3poN373N0Hwkks5AQRKIuvFC8,4517
|
481
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
487
|
+
sglang/srt/managers/cache_controller.py,sha256=RDKuRuRdrMWhsy4QOXvtTG_u_NQUQFly7a6BnoEYiMY,18434
|
482
488
|
sglang/srt/managers/configure_logging.py,sha256=fOJaXAQ1n9m-8KPJndpsKvS885i69SMafoEADLIVfIM,1633
|
483
489
|
sglang/srt/managers/data_parallel_controller.py,sha256=UgMruoTjQDWDCZK7ATmmgNrrY011pDqrFGl4vJdBpKU,11677
|
484
490
|
sglang/srt/managers/detokenizer_manager.py,sha256=3S3aRvKSi75RQSxEEQkeyxKDNNunWiw9wlwsbT1VXSo,10099
|
485
491
|
sglang/srt/managers/expert_distribution.py,sha256=r3o5RGI0gnV7xb60AApqKYa0oiSB37oB7hQBX7P3xZM,3225
|
486
|
-
sglang/srt/managers/io_struct.py,sha256=
|
492
|
+
sglang/srt/managers/io_struct.py,sha256=ipda4zV_48dIOgmO8t-rvd37jcqvhXtkM8z5PzeKtG4,31755
|
487
493
|
sglang/srt/managers/mm_utils.py,sha256=JTu5B7jZWTtZi8LCpVa6ITvSToxcuf5PDbb3FJC9M6o,18089
|
488
494
|
sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
|
489
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
490
|
-
sglang/srt/managers/schedule_policy.py,sha256=
|
491
|
-
sglang/srt/managers/scheduler.py,sha256=
|
495
|
+
sglang/srt/managers/schedule_batch.py,sha256=bPCIF6WYB5qMAhJn8f_waFF6RC3MAJ0nyRXVAkuF4SE,65030
|
496
|
+
sglang/srt/managers/schedule_policy.py,sha256=VtjzbEdpCpay9HUFrIRM68ju1vyIPX9yDZVnX03ffAE,19765
|
497
|
+
sglang/srt/managers/scheduler.py,sha256=Aujk_lnvlxpoDRpZdGPRULYD4oxg53BTpUzjGFdmJFo,90200
|
492
498
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=15Eicph3bPVuBMPsMPOLReNc2Kmi6m1WXlq0UbYtj9g,26773
|
493
499
|
sglang/srt/managers/session_controller.py,sha256=o-ifit0n4_xHLNmyD0Ams8FxGRgxFybX-Vz1hwgr3UQ,5755
|
494
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
495
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
500
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=w2zheYUZ8KHMWegPOyusJzvMqVDs3xI1Bxn9-NjrE9g,50830
|
501
|
+
sglang/srt/managers/tp_worker.py,sha256=ce2Q1AF1ZilE3Vh1Vcs4tXBkeUIl4Bm1NKv9yjX6xqs,9919
|
496
502
|
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=PyBiUdHeh1Z_o_R34lNB28SBjqTP4nArNCQhX0O6K2M,9440
|
497
503
|
sglang/srt/managers/utils.py,sha256=5i75uLlQOF_5CaT02CrWtwozMTtwTg2_nLP8Dtr-JZQ,1536
|
498
|
-
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=
|
504
|
+
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=DMeqUdxyOZ5IKo-Z2NjEteJS-Oz6gG9jyU27c8QwA5A,10367
|
499
505
|
sglang/srt/managers/multimodal_processors/clip.py,sha256=lRc2mcuDbAhZVf-0EfkO81pqDiol9zLvTpDqtPIBQ2k,1525
|
500
506
|
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=hpjpGFzlRBQ8Xv08i37X_VUhnDp_Qm2xD1_F17vK8fI,3253
|
501
507
|
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=G52ck_3UQGeyrtvjLqI8B0Tm8iNsyB_ahiMTAvx083U,2191
|
508
|
+
sglang/srt/managers/multimodal_processors/internvl.py,sha256=mydI4yWRMiIo6y8ZL_wxqU2IPpfVf2eR4SA-yOmK3H0,9172
|
502
509
|
sglang/srt/managers/multimodal_processors/janus_pro.py,sha256=UJoKQWsoU9kittKDwjWbG2KC12wSA-4A3DpTPhA6VoI,1854
|
503
510
|
sglang/srt/managers/multimodal_processors/kimi_vl.py,sha256=vC9OeS7gVTHzazbluiQ1I0QRKqszlqK75ghUA1rmUNc,2490
|
504
511
|
sglang/srt/managers/multimodal_processors/llava.py,sha256=8mac3vUUpVd12o43k1TyMaLEySZB915ks8Q5epeZmbg,6209
|
@@ -507,48 +514,49 @@ sglang/srt/managers/multimodal_processors/mlama.py,sha256=MLiGS606LzVtdoXvjWGANx
|
|
507
514
|
sglang/srt/managers/multimodal_processors/mllama4.py,sha256=50Yox7TaGrrB7iPjN1dQ_UzuY41x7VLmMcRXBhTgUvE,5592
|
508
515
|
sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=l94DOaY9vhlD-QjWVWNHUmLu48UKTb-QN9vXqrQxBgA,6907
|
509
516
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=NY62Zo0A0tLJ7ObRLOQqQcXCxoJUDZsK8f5U4dNQjKc,973
|
510
|
-
sglang/srt/mem_cache/chunk_cache.py,sha256=
|
517
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=Lyv3eUEaYnCJCLoZQhCx5WfiiUCrrS4xti3e5VROl1A,1894
|
511
518
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
512
519
|
sglang/srt/mem_cache/hiradix_cache.py,sha256=BJR-R2u5YyYIhGIxTY-3rf8Vx60XjCRU8Yhmkn2fzzM,16597
|
513
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
520
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=DG02tZ7jPRoh1_OVcvmhyHg8u-YKlEuBe9AvyB88p6Y,36260
|
514
521
|
sglang/srt/mem_cache/paged_allocator.py,sha256=BrJS0vN1k-vTSgb_M8u_1KoZFRgzgR1WRyImCTq3T0U,9770
|
515
522
|
sglang/srt/mem_cache/radix_cache.py,sha256=Lm-pco6CJ4orb9IfDpbHm5MnyK8Ya0OF1x9p88dv548,14906
|
516
523
|
sglang/srt/metrics/collector.py,sha256=zHg4twFQJvuK1mSme3-EYQa9PJryfp_u7a4RxQ5RcO0,8874
|
517
524
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
518
525
|
sglang/srt/model_executor/cuda_graph_runner.py,sha256=ISDLqpJZ0_WjX2IqWt6yASy4yLMUchVc9-6J_bK-UBY,26208
|
519
526
|
sglang/srt/model_executor/forward_batch_info.py,sha256=Kz30RuEjuOAN9_8hlvvknF4qeohyas7NrS90FCRtIMg,27730
|
520
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
527
|
+
sglang/srt/model_executor/model_runner.py,sha256=Ly2mSDbI83UBom4FHDMPIKdCqS4m_2t7O-gZWjYHnYE,49184
|
521
528
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
522
|
-
sglang/srt/model_loader/loader.py,sha256
|
529
|
+
sglang/srt/model_loader/loader.py,sha256=-TISKGKpehU86vVyGm0xo2GALVVzQSUibi3jEisTBiw,55494
|
523
530
|
sglang/srt/model_loader/utils.py,sha256=0NaMR67fESFopaklmsleiL27XH1QUrjZW246MUu1EJ0,1369
|
524
531
|
sglang/srt/model_loader/weight_utils.py,sha256=yKnau-wH9muczoCpDTCVIqXFqz-QJmEEySplX3bMJWk,32153
|
525
532
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
526
533
|
sglang/srt/models/bert.py,sha256=kHlErDgNX_mIhfWWCnAcH_ncvYg22Y61gI34gW8GuUY,12738
|
527
534
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
528
|
-
sglang/srt/models/clip.py,sha256=
|
535
|
+
sglang/srt/models/clip.py,sha256=58m-y5lkHIGY0ypYGtgD6gImQ7yZJutYGVl-ygqbNBI,19765
|
529
536
|
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
530
537
|
sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,15598
|
531
538
|
sglang/srt/models/deepseek.py,sha256=ZnN02HdgXCB23Vno5V9UMUoOxH5HC82vNTwsVulUJ-o,17206
|
532
|
-
sglang/srt/models/deepseek_janus_pro.py,sha256=
|
533
|
-
sglang/srt/models/deepseek_nextn.py,sha256=
|
534
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
539
|
+
sglang/srt/models/deepseek_janus_pro.py,sha256=9pQyTzKPTJI0tbOs0aPfqfqMeZeY-ZyyDiNjhkvNxZ8,70449
|
540
|
+
sglang/srt/models/deepseek_nextn.py,sha256=Yy5dItwimszQsAN7EjgND2cNQ9bypJ1TtFfhqcBQJnk,5673
|
541
|
+
sglang/srt/models/deepseek_v2.py,sha256=qCTwb5d2Tem2hgH0_lBb2auIfn9TUSaO_D4-yzfYX08,75561
|
535
542
|
sglang/srt/models/deepseek_vl2.py,sha256=j8BdxZsMjm6lPdbDipEIKhVIVywCP1Vl1Kl46BZ5_0Y,13147
|
536
543
|
sglang/srt/models/exaone.py,sha256=rX7J0xFt9TSt6tMIhnYMkb5KDnqTJIV4BtjPLFwQ8_8,13425
|
537
544
|
sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
|
538
545
|
sglang/srt/models/gemma2.py,sha256=kqtwdo93GWKm2iBN29RoIRH2ggRm-K_80LM5btgfBLo,16395
|
539
546
|
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
540
547
|
sglang/srt/models/gemma3_causal.py,sha256=LfwHhF0nRD7OnmeHXXfQ7rofnFXjJI74gZiptak18RY,24924
|
541
|
-
sglang/srt/models/gemma3_mm.py,sha256=
|
548
|
+
sglang/srt/models/gemma3_mm.py,sha256=5rthHzaFNJb82IYUREwxQt4N4fDXW4lIxiptnKpVing,15246
|
542
549
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
543
550
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
544
551
|
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
545
552
|
sglang/srt/models/grok.py,sha256=vESZeGS4adI_JAerXIkCcTm15-CNiGeS7VHc36C6w1A,28033
|
546
|
-
sglang/srt/models/internlm2.py,sha256=
|
553
|
+
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
547
554
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
555
|
+
sglang/srt/models/internvl.py,sha256=kEzkL5tAq3skvK5D7TqhiElSIXrA6cNOd8irYV4aKhA,24927
|
548
556
|
sglang/srt/models/kimi_vl.py,sha256=YoM6CmrF4ZS0SsXKiR-_SfylKhd87ciJjno6_x5LG4o,12874
|
549
557
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
550
|
-
sglang/srt/models/llama.py,sha256=
|
551
|
-
sglang/srt/models/llama4.py,sha256=
|
558
|
+
sglang/srt/models/llama.py,sha256=ELNq-rheXbf1_YEFhg-AfuoPTPP0rF6mp1p-r0njGjA,26998
|
559
|
+
sglang/srt/models/llama4.py,sha256=Nd78ymcCzflazaFehYc1YGzZLbLfHgFl8dJXmhYmcEE,19402
|
552
560
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
553
561
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
554
562
|
sglang/srt/models/llama_eagle3.py,sha256=KCvUrWn17t7T28G60HwMyy99iB9AbdbPnS2el9n3r6o,6804
|
@@ -559,39 +567,40 @@ sglang/srt/models/llavavid.py,sha256=q0lHlRnoYHKJZsWnkIQdd6dYAQ26t7XsmrqA0zDGmZc
|
|
559
567
|
sglang/srt/models/minicpm.py,sha256=m5HFsSJj0Po09LY9R6qj6K4gceqWDMOePz3NDGgMGT4,14691
|
560
568
|
sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
|
561
569
|
sglang/srt/models/minicpmo.py,sha256=BAiFR78L0j5WDZtOrUf6JgUe9DZs9huIsfQ_4RzUbdA,76319
|
562
|
-
sglang/srt/models/minicpmv.py,sha256=
|
570
|
+
sglang/srt/models/minicpmv.py,sha256=hSDWEcmutqOJv-xs0X_4TaNCDAWFUk71eRHLm9sPC0U,40564
|
563
571
|
sglang/srt/models/mistral.py,sha256=EYifJUUzN2Z2-iL37eJiNZF_DB0H4pa0mKlgYRIxM70,838
|
564
572
|
sglang/srt/models/mixtral.py,sha256=zQHCL_ZMKmLR7jitpEw8n7Rv6xhxUJzSXklsw6auh2E,14965
|
565
573
|
sglang/srt/models/mixtral_quant.py,sha256=-kQw9r8KcLdO8SNN9RKXzrGq9Q2Al9l9cWHi1VrZSRM,15260
|
566
|
-
sglang/srt/models/mllama.py,sha256=
|
574
|
+
sglang/srt/models/mllama.py,sha256=sOuP3Od3h9_uh_oxDN5rj4CzhZjg82PyElfBHuTxzUQ,39768
|
567
575
|
sglang/srt/models/mllama4.py,sha256=ejuhIVX0MDojdB5EPR-V-Qd_E9st8KYjnjyeArFbdFs,9084
|
568
576
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
569
577
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
570
578
|
sglang/srt/models/olmoe.py,sha256=TMzt-yB891bvA4X50xL0NjNnFYSx9imlA7N1EG8KNK0,15949
|
571
|
-
sglang/srt/models/phi3_small.py,sha256=
|
579
|
+
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
572
580
|
sglang/srt/models/qwen.py,sha256=xYkVmMZS2uMqWhfndc8EYm0olpKFnggfuMp_6aobVi4,10758
|
573
581
|
sglang/srt/models/qwen2.py,sha256=ab912Yyk0aXOzI-wrxqN-sNF3bTVkNxB8P2uNcOCv9U,16394
|
574
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
582
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=LQee0Yuz6XzKiIFZQBUgRuDN2aX_CqvoxHx7w5a35ww,22603
|
575
583
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
576
584
|
sglang/srt/models/qwen2_eagle.py,sha256=Iz0HWL2FgSD3FqoFhfYmbIZeEYkPTJ96lYbkncmHJX4,4644
|
577
585
|
sglang/srt/models/qwen2_moe.py,sha256=iG0d2WwUosOFR9w2YGM9CfvZ1NG-rhse3OUTwSs8a6Q,18567
|
578
586
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
579
|
-
sglang/srt/models/qwen2_vl.py,sha256=
|
587
|
+
sglang/srt/models/qwen2_vl.py,sha256=X18_Smisiz6zQHUK4h7-ho8poRKWjUZisjB5LuUwYGk,20946
|
580
588
|
sglang/srt/models/qwen3.py,sha256=reaowGkotYAGHS5zTCWrvnyxtu92QKus19n-2amtMa4,12358
|
581
589
|
sglang/srt/models/qwen3_moe.py,sha256=A9Z3OhJqld1sJUDsHymgGxib4lMCMTKxF8iIzHDGdNo,15877
|
582
590
|
sglang/srt/models/registry.py,sha256=inKh9iwOp3LFYm3nqujg-OtABClOP-ifc1stA9cZegA,3434
|
583
591
|
sglang/srt/models/roberta.py,sha256=Zgd35och3pW6TYrNeEoeOZ8qPfbFwB3ngThpVWSPBcY,6320
|
584
592
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
585
593
|
sglang/srt/models/torch_native_llama.py,sha256=5tfFSMAXB3ScToqTALtCXa8Oo-qPCJh-KQCNB6QOlNA,19293
|
594
|
+
sglang/srt/models/xiaomi_mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
586
595
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
587
596
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
588
597
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
589
|
-
sglang/srt/openai_api/adapter.py,sha256
|
590
|
-
sglang/srt/openai_api/protocol.py,sha256=
|
598
|
+
sglang/srt/openai_api/adapter.py,sha256=-BDvis2oTREf54GBsvWyot9sv3uTgyvnKLEeAFhQLiI,77004
|
599
|
+
sglang/srt/openai_api/protocol.py,sha256=AHJkOvQfdYk4OkP6amSGdRKJAyfPoGW3iZ5qnUREFO0,14856
|
591
600
|
sglang/srt/platforms/interface.py,sha256=hym3iooBB4C8if5hDZezgVN6h4NIOu7sg2ZUBIV6XmM,11246
|
592
601
|
sglang/srt/sampling/custom_logit_processor.py,sha256=tDvoLgLqn-sy1qcY6vSrpbnHCeqbdk0uhMOO-uy4p4E,1099
|
593
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
594
|
-
sglang/srt/sampling/sampling_params.py,sha256=
|
602
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=UxM025exqxa6yg_T40D5jNpluTFWjLT6wlDiyK0r014,14207
|
603
|
+
sglang/srt/sampling/sampling_params.py,sha256=xGo939Ai-_qUAvVEomZtuFN7U3Iro70Kpq42yXadyXk,6013
|
595
604
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
596
605
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
597
606
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
@@ -615,19 +624,20 @@ sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWU
|
|
615
624
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
616
625
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
617
626
|
sglang/test/test_activation.py,sha256=GeTIJHxlLQfW3kM-X1FGa8Sa3dSGKHEXl5wEy-hfGis,1489
|
618
|
-
sglang/test/test_block_fp8.py,sha256=
|
627
|
+
sglang/test/test_block_fp8.py,sha256=bsV6Y_tCUF2ROEmuPDegNmHzGF-T4AgOvH7eYmAmKtA,21604
|
619
628
|
sglang/test/test_block_fp8_ep.py,sha256=N1rvqbPErBaFFpeAw8TLYXGNZOoG7cfIBP2p5XbSyMo,10806
|
620
629
|
sglang/test/test_custom_ops.py,sha256=2bSo9P5_rJZYFq8Y8IKRimDfFyZZGJluhL7Ngny0Pf4,5571
|
630
|
+
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
621
631
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
622
632
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
623
633
|
sglang/test/test_programs.py,sha256=VZ3vXtUDBnXz0M7gFdDH8hXg9Wa0j_qI8CVqjEgRN_E,18877
|
624
|
-
sglang/test/test_utils.py,sha256=
|
634
|
+
sglang/test/test_utils.py,sha256=trMVLChmuCqq6Cue-9zP8b8tsx0V29HTJwygk2fQR0E,33042
|
625
635
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
626
636
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
627
637
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
628
638
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=er0i3KGHMkw-4UZB1GCFd4oYwRcXfU5wpO1ORqpNGGA,7626
|
629
|
-
sglang-0.4.6.
|
630
|
-
sglang-0.4.6.
|
631
|
-
sglang-0.4.6.
|
632
|
-
sglang-0.4.6.
|
633
|
-
sglang-0.4.6.
|
639
|
+
sglang-0.4.6.post3.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
640
|
+
sglang-0.4.6.post3.dist-info/METADATA,sha256=qB8YbUsae_tEFg_DyQ1UqA4VcSotC3QL700-YFw3bco,25930
|
641
|
+
sglang-0.4.6.post3.dist-info/WHEEL,sha256=DnLRTWE75wApRYVsjgc6wsVswC54sMSJhAEd4xhDpBk,91
|
642
|
+
sglang-0.4.6.post3.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
643
|
+
sglang-0.4.6.post3.dist-info/RECORD,,
|
File without changes
|
File without changes
|