sglang 0.4.7__py3-none-any.whl → 0.4.7.post1__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/__init__.py +2 -0
- sglang/api.py +7 -0
- sglang/bench_serving.py +1 -1
- sglang/lang/interpreter.py +40 -1
- sglang/lang/ir.py +27 -0
- sglang/math_utils.py +8 -0
- sglang/srt/configs/model_config.py +6 -0
- sglang/srt/conversation.py +6 -0
- sglang/srt/disaggregation/base/__init__.py +1 -1
- sglang/srt/disaggregation/base/conn.py +25 -11
- sglang/srt/disaggregation/common/__init__.py +5 -1
- sglang/srt/disaggregation/common/utils.py +42 -0
- sglang/srt/disaggregation/decode.py +196 -51
- sglang/srt/disaggregation/fake/__init__.py +1 -1
- sglang/srt/disaggregation/fake/conn.py +15 -9
- sglang/srt/disaggregation/mooncake/__init__.py +1 -1
- sglang/srt/disaggregation/mooncake/conn.py +18 -13
- sglang/srt/disaggregation/nixl/__init__.py +6 -1
- sglang/srt/disaggregation/nixl/conn.py +17 -12
- sglang/srt/disaggregation/prefill.py +128 -43
- sglang/srt/disaggregation/utils.py +127 -123
- sglang/srt/entrypoints/engine.py +15 -1
- sglang/srt/entrypoints/http_server.py +13 -2
- sglang/srt/eplb_simulator/__init__.py +1 -0
- sglang/srt/eplb_simulator/reader.py +51 -0
- sglang/srt/layers/activation.py +19 -0
- sglang/srt/layers/attention/aiter_backend.py +15 -2
- sglang/srt/layers/attention/cutlass_mla_backend.py +38 -15
- sglang/srt/layers/attention/flashattention_backend.py +53 -64
- sglang/srt/layers/attention/flashinfer_backend.py +1 -2
- sglang/srt/layers/attention/flashinfer_mla_backend.py +22 -24
- sglang/srt/layers/attention/flashmla_backend.py +2 -10
- sglang/srt/layers/attention/triton_backend.py +119 -119
- sglang/srt/layers/attention/triton_ops/decode_attention.py +2 -7
- sglang/srt/layers/attention/vision.py +51 -24
- sglang/srt/layers/communicator.py +23 -5
- sglang/srt/layers/linear.py +0 -4
- sglang/srt/layers/logits_processor.py +0 -12
- sglang/srt/layers/moe/ep_moe/kernels.py +6 -5
- sglang/srt/layers/moe/ep_moe/layer.py +42 -32
- sglang/srt/layers/moe/ep_moe/token_dispatcher.py +11 -37
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +1 -4
- sglang/srt/layers/moe/topk.py +16 -8
- sglang/srt/layers/pooler.py +56 -0
- sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py +1 -0
- sglang/srt/layers/quantization/{deep_gemm.py → deep_gemm_wrapper/compile_utils.py} +23 -80
- sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py +32 -0
- sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py +110 -0
- sglang/srt/layers/quantization/fp8_kernel.py +44 -15
- sglang/srt/layers/quantization/fp8_utils.py +87 -22
- sglang/srt/layers/radix_attention.py +2 -3
- sglang/srt/lora/lora_manager.py +79 -34
- sglang/srt/lora/mem_pool.py +4 -5
- sglang/srt/managers/cache_controller.py +2 -1
- sglang/srt/managers/io_struct.py +28 -4
- sglang/srt/managers/multimodal_processors/base_processor.py +2 -2
- sglang/srt/managers/multimodal_processors/vila.py +85 -0
- sglang/srt/managers/schedule_batch.py +39 -6
- sglang/srt/managers/scheduler.py +73 -17
- sglang/srt/managers/tokenizer_manager.py +29 -2
- sglang/srt/mem_cache/chunk_cache.py +1 -0
- sglang/srt/mem_cache/hiradix_cache.py +4 -2
- sglang/srt/mem_cache/memory_pool.py +111 -407
- sglang/srt/mem_cache/memory_pool_host.py +380 -0
- sglang/srt/mem_cache/radix_cache.py +36 -12
- sglang/srt/model_executor/cuda_graph_runner.py +122 -55
- sglang/srt/model_executor/forward_batch_info.py +14 -5
- sglang/srt/model_executor/model_runner.py +6 -6
- sglang/srt/model_loader/loader.py +8 -1
- sglang/srt/models/bert.py +113 -13
- sglang/srt/models/deepseek_v2.py +113 -155
- sglang/srt/models/internvl.py +46 -102
- sglang/srt/models/roberta.py +117 -9
- sglang/srt/models/vila.py +305 -0
- sglang/srt/openai_api/adapter.py +162 -4
- sglang/srt/openai_api/protocol.py +37 -1
- sglang/srt/sampling/sampling_batch_info.py +24 -0
- sglang/srt/sampling/sampling_params.py +2 -0
- sglang/srt/server_args.py +318 -233
- sglang/srt/speculative/build_eagle_tree.py +1 -1
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +4 -3
- sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py +5 -2
- sglang/srt/speculative/eagle_utils.py +389 -109
- sglang/srt/speculative/eagle_worker.py +134 -43
- sglang/srt/two_batch_overlap.py +4 -2
- sglang/srt/utils.py +58 -0
- sglang/test/attention/test_prefix_chunk_info.py +2 -0
- sglang/test/runners.py +38 -3
- sglang/test/test_block_fp8.py +1 -0
- sglang/test/test_block_fp8_deep_gemm_blackwell.py +252 -0
- sglang/test/test_block_fp8_ep.py +1 -0
- sglang/test/test_utils.py +3 -1
- sglang/utils.py +9 -0
- sglang/version.py +1 -1
- {sglang-0.4.7.dist-info → sglang-0.4.7.post1.dist-info}/METADATA +5 -5
- {sglang-0.4.7.dist-info → sglang-0.4.7.post1.dist-info}/RECORD +99 -88
- {sglang-0.4.7.dist-info → sglang-0.4.7.post1.dist-info}/WHEEL +0 -0
- {sglang-0.4.7.dist-info → sglang-0.4.7.post1.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.7.dist-info → sglang-0.4.7.post1.dist-info}/top_level.txt +0 -0
@@ -1,23 +1,24 @@
|
|
1
|
-
sglang/__init__.py,sha256=
|
2
|
-
sglang/api.py,sha256=
|
1
|
+
sglang/__init__.py,sha256=x1v8748WXS2BAptWAd5fR3YBEkngC7e_P_rkCNuNCGg,1702
|
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=fCxRRk14uQqTxpriBkrUkvrOUjNT7TZgDeGGWJQzhgw,19328
|
5
5
|
sglang/bench_one_batch_server.py,sha256=4Jbs8UI-Sbt3TL3SJBC3fySZPe4apz2glKWOvvaYsQQ,13486
|
6
|
-
sglang/bench_serving.py,sha256=
|
6
|
+
sglang/bench_serving.py,sha256=EzZn91DuScAEhUMQv-LPWm3UoGjzj8OEzHMzVwoEA34,65672
|
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
|
11
12
|
sglang/profiler.py,sha256=tEHzHerXC-ymk4OrkoUcMbgcGHmb8VESthsNSP2Yx9w,4417
|
12
|
-
sglang/utils.py,sha256=
|
13
|
-
sglang/version.py,sha256=
|
13
|
+
sglang/utils.py,sha256=VH6zrnkjzcR3DE__WfVph6wswJ4JuzoQD47VmbZ38eI,16435
|
14
|
+
sglang/version.py,sha256=rkzrlJTNQdK78CIF17Jk3y_9tOj5bACvLDEnSq4qJRw,28
|
14
15
|
sglang/eval/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
15
16
|
sglang/eval/loogle_eval.py,sha256=pRPVA4fxGmT3_oXvXnlNE-UlPrcQGLBJF-OSE9YWJXM,4336
|
16
17
|
sglang/lang/chat_template.py,sha256=HKlx7snSWFED8GKF5ex79sQrPWFw5TSXQM0_LsiD9Bc,20552
|
17
18
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
18
19
|
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
19
|
-
sglang/lang/interpreter.py,sha256=
|
20
|
-
sglang/lang/ir.py,sha256=
|
20
|
+
sglang/lang/interpreter.py,sha256=JneG-Yw-XyOTBZCIoxTiQluQjAlSz1YswnV0l6pqVPo,34811
|
21
|
+
sglang/lang/ir.py,sha256=FnRJ-lndAsR4GR0ONJRPDtlYx8FvL9RIk44vSA16RBk,19656
|
21
22
|
sglang/lang/tracer.py,sha256=ljBo9VZ0zVaGwzNk32qw21acyo60N0UjIjqBbT5a1WI,8175
|
22
23
|
sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
23
24
|
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
@@ -29,7 +30,7 @@ sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZ
|
|
29
30
|
sglang/srt/_custom_ops.py,sha256=Y56OZL-6cUBLVmCpWSSjmpsisRYbSE9H--Oq8NjzbPM,4437
|
30
31
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
31
32
|
sglang/srt/code_completion_parser.py,sha256=vafJqdTTreD9kvCsoMuxP_fFmoue7pOA1ibI9KXg4mE,5405
|
32
|
-
sglang/srt/conversation.py,sha256=
|
33
|
+
sglang/srt/conversation.py,sha256=Ep72tO6lJ7vpyhCmzp5AGmrjDwc2VkegLs2gIklGm4g,36628
|
33
34
|
sglang/srt/custom_op.py,sha256=lIwo6blTAaPUqXnxy1xsmUJ0qCdp9poPKbZ4mRJAaN4,2734
|
34
35
|
sglang/srt/debug_utils.py,sha256=slaFOY4BYDBFatkfu8FZlzai-u4LFS-5GUzdr-t50zE,2241
|
35
36
|
sglang/srt/hf_transformers_utils.py,sha256=S1ZF4aFKTocenXvj9ti6M-buiCBus4FrP1AdwFz_Wbw,11943
|
@@ -39,10 +40,10 @@ sglang/srt/operations.py,sha256=ddQ8KO63L73OciaR8MZ9h2h83gKVY4-WuWgeEGowPJA,5346
|
|
39
40
|
sglang/srt/operations_strategy.py,sha256=6DDLEdmkLrFDTXWZoFO0q9MZjEThvfyvoO-LbQsNpPQ,7023
|
40
41
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
41
42
|
sglang/srt/reasoning_parser.py,sha256=lZN5b1TJp3EK2GzxcICQhp0tRQjQw3ROOrjRgQe6Bsc,6341
|
42
|
-
sglang/srt/server_args.py,sha256=
|
43
|
+
sglang/srt/server_args.py,sha256=nz73pQa4Z6mI-2elebYMV0ajq3QLH1dQ3OBslp-G7wU,71676
|
43
44
|
sglang/srt/torch_memory_saver_adapter.py,sha256=HYlgYJ2sgmjs2RSjU2KbCaXijRg3mTDZ0ZcCB5Bt6Ps,2211
|
44
|
-
sglang/srt/two_batch_overlap.py,sha256=
|
45
|
-
sglang/srt/utils.py,sha256=
|
45
|
+
sglang/srt/two_batch_overlap.py,sha256=Q6tobqItnlK5ad9mqqMMx0HJ-PAzW4DgBtgSQ7Ax6sM,21848
|
46
|
+
sglang/srt/utils.py,sha256=Zl-xEOFgPyr91A9-q-0Y1PUobAmKvKURgSDR3EBGk4U,72516
|
46
47
|
sglang/srt/warmup.py,sha256=FmJiYfjRr3X_eAe7ojQaPoN17LvHpjDmRWRnO-k86AQ,1469
|
47
48
|
sglang/srt/configs/__init__.py,sha256=8EcVRP95epZ49DxBa6LgKWt7eO3Qe7Hrr3V1c6HkMnY,553
|
48
49
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
@@ -55,7 +56,7 @@ sglang/srt/configs/janus_pro.py,sha256=Rrb7kQsNaUP-TiZrjNk8Lr1momFrql8ScEunnrH0_
|
|
55
56
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
56
57
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
57
58
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
58
|
-
sglang/srt/configs/model_config.py,sha256=
|
59
|
+
sglang/srt/configs/model_config.py,sha256=mXERUkexcWnZxrCzpxaMo7FhYm-CNhwttDIVhw-ZysY,25206
|
59
60
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
60
61
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
61
62
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -72,24 +73,25 @@ sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCX
|
|
72
73
|
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
73
74
|
sglang/srt/constrained/xgrammar_backend.py,sha256=u9Ao-XX22UzALkATEAR_-0EoyBTxMTJV590qd9LAUHM,7906
|
74
75
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
75
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
76
|
+
sglang/srt/disaggregation/decode.py,sha256=vkxzLt843pcUe9gQI2M--25fyzCKpi0iGrLa7QPKFhA,33128
|
76
77
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=cUfd3-5lRHqWpwkrj4xdGMV2Hus08hdQbobTLNoCXlo,5569
|
77
78
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
78
79
|
sglang/srt/disaggregation/launch_lb.py,sha256=mcbAztN4gnHevw_T5R2_nWsymsDEY9vHkm7OJ1vr6cc,4211
|
79
80
|
sglang/srt/disaggregation/mini_lb.py,sha256=WGEdKQ0jMyRtZ1gG6q8uPnP9ovXkWGQamWZ3YmS4ng4,13429
|
80
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
81
|
-
sglang/srt/disaggregation/utils.py,sha256=
|
82
|
-
sglang/srt/disaggregation/base/__init__.py,sha256=
|
83
|
-
sglang/srt/disaggregation/base/conn.py,sha256=
|
84
|
-
sglang/srt/disaggregation/common/__init__.py,sha256=
|
81
|
+
sglang/srt/disaggregation/prefill.py,sha256=xj_Q5NT0DP-5bxV0Hct6PnevAVbG0ZA5r3dTcT1ivRo,23102
|
82
|
+
sglang/srt/disaggregation/utils.py,sha256=ih7KiJxyZF9Ma7O09UpBqkm8OCgfOvlg4odtoCK4uy4,10312
|
83
|
+
sglang/srt/disaggregation/base/__init__.py,sha256=4VwUv0aWxwmVL1049XK82aLTNxmt0WY5RPy9li-wyVk,160
|
84
|
+
sglang/srt/disaggregation/base/conn.py,sha256=6KK_7HL7xixVSB8iap8jjJrIv3JgHDmynZ39Os3k5MU,2771
|
85
|
+
sglang/srt/disaggregation/common/__init__.py,sha256=7yl-EGLMVKRpBUaGF_7lwAsw2J_mqpRZV0238VGxD9o,126
|
85
86
|
sglang/srt/disaggregation/common/conn.py,sha256=CZR1lMCE_mpSkvjc6BBmSr1SbHY1uZuxjpanazD-YXc,16071
|
86
|
-
sglang/srt/disaggregation/
|
87
|
-
sglang/srt/disaggregation/fake/
|
88
|
-
sglang/srt/disaggregation/
|
89
|
-
sglang/srt/disaggregation/mooncake/
|
87
|
+
sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeKVPMWPcB5ywbE,1194
|
88
|
+
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
89
|
+
sglang/srt/disaggregation/fake/conn.py,sha256=oD1DArn1yDFZCu-X6p93uSLlAXEkt9lYxERICMznxGw,2286
|
90
|
+
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
91
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=udV5-9Bg1CzBXAQasCYxdcxHmwTCGss4CHmsn7Vb_Rs,47871
|
90
92
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=gOcjZPtksJDq4iiIs0_zREdOM8trqUcmOXkrj-wiCuU,3149
|
91
|
-
sglang/srt/disaggregation/nixl/__init__.py,sha256=
|
92
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
93
|
+
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
94
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=KzVPRH8MaOAiG9EdfDN31sE9U9Ibsj2McDlSRWzHiP0,18055
|
93
95
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
94
96
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
95
97
|
sglang/srt/distributed/parallel_state.py,sha256=l4vrGXIr9ykd0imtzKdMjnBrQPRvbrYg0jQ9trDkdzI,53527
|
@@ -105,10 +107,12 @@ sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6
|
|
105
107
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=d8mykYmXM1lfbPm8GNtqCF0Un_pdXYjbNmsgoVFyyow,20874
|
106
108
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
107
109
|
sglang/srt/entrypoints/EngineBase.py,sha256=FCwqQMJE_8CCCMThAXUZaKafsHvh2BaQ31J-7_ormwA,2310
|
108
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
109
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
110
|
+
sglang/srt/entrypoints/engine.py,sha256=SkBxdo6UDcQBOHbfpcfGrXsv0To92j_3BsdkA3Z6y1Y,30316
|
111
|
+
sglang/srt/entrypoints/http_server.py,sha256=F-yBo8nKYhFqi-WYvrHOGLmWpghEUqsc__BzB7xjlcI,31965
|
110
112
|
sglang/srt/entrypoints/http_server_engine.py,sha256=0QJFmrKAVnBmFbObHrmvUDcxDAsvnv6H29cQq286CKc,4939
|
111
113
|
sglang/srt/entrypoints/verl_engine.py,sha256=RYizNetTHzcB8dErX1EW4NsyRNGkFPljYaAf7pVRPdM,7002
|
114
|
+
sglang/srt/eplb_simulator/__init__.py,sha256=HIZaXqsvsOCMMJ81dSs1afSGZ5G6OiOZEtHpltyzzjY,21
|
115
|
+
sglang/srt/eplb_simulator/reader.py,sha256=R9wV7PqaCjILSnfYk90hNY95iJeST08a55Uj2Qk4iE0,1832
|
112
116
|
sglang/srt/function_call/base_format_detector.py,sha256=Ol8VaVrilkBhnjUUmWlt6E0eazvFd5gFrzNx0_x0_iw,12755
|
113
117
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
114
118
|
sglang/srt/function_call/deepseekv3_detector.py,sha256=FO5wbBMj1l9culkmZeC-LKguyRuqHcQOyX7NCEgfzTQ,8962
|
@@ -119,38 +123,38 @@ sglang/srt/function_call/mistral_detector.py,sha256=D2udBa9K1J6DdSPyJCp6JpaqYnrO
|
|
119
123
|
sglang/srt/function_call/pythonic_detector.py,sha256=waFdfHJuNg9DanTRDNWgh-Ji8TQkebcldUDPj0Xm8kk,8723
|
120
124
|
sglang/srt/function_call/qwen25_detector.py,sha256=YYDXHBcW1EQpZd0xzL92E6NBLG5t6vqPYOmFRACMdcw,4874
|
121
125
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
122
|
-
sglang/srt/layers/activation.py,sha256=
|
123
|
-
sglang/srt/layers/communicator.py,sha256=
|
126
|
+
sglang/srt/layers/activation.py,sha256=GNp9qww-EF6JCvTY5_FVWtqodr2j6m0lhP7vmksnBNo,6647
|
127
|
+
sglang/srt/layers/communicator.py,sha256=_H-ZkyDeu8Y1v4BkeiexHKsx2MK3qQCPFodoMqxN80U,18639
|
124
128
|
sglang/srt/layers/dp_attention.py,sha256=oQ8qMzcv3r-x0GW8_j_D-BaGIM5BhQ_ehi-TkqIE4O4,9274
|
125
129
|
sglang/srt/layers/elementwise.py,sha256=XCrR2i-9dP-H6jQo2zUuquwZrsl_wEQqj5Wxk6WUf7o,13987
|
126
130
|
sglang/srt/layers/layernorm.py,sha256=VW46eTmFLFo7KezfwMKvwXlC_NPUVMGb93K2WREgldY,6325
|
127
|
-
sglang/srt/layers/linear.py,sha256=
|
128
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
131
|
+
sglang/srt/layers/linear.py,sha256=xdAv5qJodLdapHi9ex3e0Qa_KHldcGwEiE-LpLRs1U8,51939
|
132
|
+
sglang/srt/layers/logits_processor.py,sha256=KGYC4rPTLCHRnV-yL2E3ACj-bxO0BVZcQ_ZEUl9UNgk,25207
|
129
133
|
sglang/srt/layers/multimodal.py,sha256=YVR69WW-2aGDcZHT8IVJ6F_LRM7wraZr8VjrPDXqDmA,2104
|
130
134
|
sglang/srt/layers/parameter.py,sha256=zqWyEzpWzP4NNTjq3G9khq6XofgpcmJqQLg6Vd4WyWE,15084
|
131
|
-
sglang/srt/layers/pooler.py,sha256=
|
132
|
-
sglang/srt/layers/radix_attention.py,sha256=
|
135
|
+
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
136
|
+
sglang/srt/layers/radix_attention.py,sha256=IlqRB4bk06FOH05_7zB8lik0xLpys7jFooLeCwdO0j8,3437
|
133
137
|
sglang/srt/layers/rotary_embedding.py,sha256=G70hvJbPV0Jeh80wuEUCNc2AKB-P9sJIscPHoRvoFT0,48011
|
134
138
|
sglang/srt/layers/sampler.py,sha256=h30VHnKyNVtTkRvOhQWIAFvCY1abx2fw1d5zeE8N57o,11169
|
135
139
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
136
140
|
sglang/srt/layers/utils.py,sha256=IWGg1Hb7c33Z3LHRPVJyUAzp3BnSid23ZWXAmJ_Jvp8,1204
|
137
141
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=GPKCQiR2yH5Z2XSE9g3vWObdegcwPnMHXv7qEZovLH4,22755
|
138
|
-
sglang/srt/layers/attention/aiter_backend.py,sha256=
|
142
|
+
sglang/srt/layers/attention/aiter_backend.py,sha256=CXFcu-PwUjhhQj02AWQop3lUzsvAF3K5OsGjz0Qahqs,32797
|
139
143
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=HCdOMceZQAmIzZTewwp1_EIRfb1URlQZ3uGUmDKWw-o,3445
|
140
|
-
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=
|
144
|
+
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=cZzKjxN7pm0J75dDrKMNKSaMVbZZGncM9mXS9CwqWLI,9784
|
141
145
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
142
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
143
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
144
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
145
|
-
sglang/srt/layers/attention/flashmla_backend.py,sha256=
|
146
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=9U2_gxJZafBoSPUM34sVtYxESHBHCnyZVr6eUHEjJWU,92296
|
147
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=a2PsYEoNrmZ7aXG9FDcPebkaBgUQ5DOcf5AWtte7yi0,49567
|
148
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=I_94zj9BlbUPc9Do4E2WE75xUA05xB_QZWYOvWv6hvI,33957
|
149
|
+
sglang/srt/layers/attention/flashmla_backend.py,sha256=spXbr5Dtl9u4saiBcxAFbsDktbidexQIpvX6J2ZffZA,20615
|
146
150
|
sglang/srt/layers/attention/intel_amx_backend.py,sha256=hH9lxXs_o66_IVs58oPhRCOXGUrHbXSz82FKtHr9GO8,4092
|
147
151
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
148
152
|
sglang/srt/layers/attention/tbo_backend.py,sha256=5EuuVA3MEeooQ5jkvANYODZc92lVlTRuijo0ZELixDw,8092
|
149
153
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=RsI4lYiQJAj-Xy0vKkzbyKOWHAVPOD9b0n0dEehwlos,9496
|
150
|
-
sglang/srt/layers/attention/triton_backend.py,sha256=
|
154
|
+
sglang/srt/layers/attention/triton_backend.py,sha256=Ao6hoiknuOKuXT6kGltMHbYEx1dCM00C3EzbwvyyPSk,36644
|
151
155
|
sglang/srt/layers/attention/utils.py,sha256=KiRSIHaGBhErUhPWCSD3Uiaqb0pSEF0NJFwTTQXoMks,2887
|
152
|
-
sglang/srt/layers/attention/vision.py,sha256
|
153
|
-
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=
|
156
|
+
sglang/srt/layers/attention/vision.py,sha256=-wGBZs9TSY8px-KidPQpEevZiQd577HJ-Wl5cTKQgWM,16291
|
157
|
+
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=eN0Lqpu5h27lMPuRnisX4jrU0WR061pCFSrh3vLlSD0,18936
|
154
158
|
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
155
159
|
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=ImpCuxszoeVdr6wzaLR3OGW3-50P9EAEvsRCdUVIrxE,14261
|
156
160
|
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
@@ -160,13 +164,13 @@ sglang/srt/layers/moe/cutlass_moe.py,sha256=--bNTA2BGbHeULb_XXDoRUyWWbE-doHo5K5k
|
|
160
164
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
161
165
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=FIES6H7oS-XjwVsWSrAkQzTdnp7kq-Z5VoViqOHpmtg,4851
|
162
166
|
sglang/srt/layers/moe/router.py,sha256=5Aeqoix_AS4uymb665OJE904wVSBkQeFdZP4e7KKPvg,10530
|
163
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
167
|
+
sglang/srt/layers/moe/topk.py,sha256=7l3oouJSdVfwT0KyZce74EKk5y7otFjGhGmL8IQWIX4,15216
|
164
168
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
165
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
166
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
167
|
-
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=
|
169
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=EhCYANB_y1_NpW-mYDMw0jYCzftlVNLcm4fqbB4xK7I,34975
|
170
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=sXwTcjWeC1Ka_UW3Jzu7tG4PXXIEZvKiOEEdzrqt190,45006
|
171
|
+
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=wPc0ewfBeoyYmgKMbp1YoT81OaJSme7AmftrXbxR7Jg,23523
|
168
172
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
|
169
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
173
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=sIv67ShhS-6QeZxncNN_R_sH_SbfL2uW7yUAs8xolN0,62952
|
170
174
|
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=ptJveWp0alXFiwvL6FyXOH5Us4YPbKj4bg5om8JuEmE,27073
|
171
175
|
"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
|
172
176
|
"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
|
@@ -333,10 +337,9 @@ sglang/srt/layers/quantization/__init__.py,sha256=isMl8LINJFMzEse4r2Ta_7JXT15eKC
|
|
333
337
|
sglang/srt/layers/quantization/awq.py,sha256=KemDG55U3B6YZVjMV71awVAIj0islFvtxcUHmOBeGy0,6739
|
334
338
|
sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
|
335
339
|
sglang/srt/layers/quantization/blockwise_int8.py,sha256=vWyPZsRLhdKtSmjvlT5fsowBK_nEebYbDAUh2yqseGw,15285
|
336
|
-
sglang/srt/layers/quantization/deep_gemm.py,sha256=TrIPU-U2vBpzsRXqw_GllJhAFH-RSxA1KuQNsggKOcM,13134
|
337
340
|
sglang/srt/layers/quantization/fp8.py,sha256=Odr96VvYrnPhJR-bH7_JZlduqd_6ikihjZQ1EhoGuQ8,44474
|
338
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=
|
339
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=
|
341
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=pUda_glnAprnFIj3VUgCUYMKb2-uK3UOC3yPahgRMBQ,34743
|
342
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=_90Js9EwurcSKIr69_6avEXbX3--Nd9LicRkRU6CGts,25580
|
340
343
|
sglang/srt/layers/quantization/gptq.py,sha256=d1frUjvXmZfQKkcMQY5t0BA4sXWHE9Jze24qxniptJE,26719
|
341
344
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
342
345
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
@@ -507,11 +510,15 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
507
510
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=PD4AJYCkHfy2ivv9baMouFXzBTy0eKMumbAfxfm91HI,3256
|
508
511
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=FImA-TJ_tQDjqwoNWxS--sRDoKDXf9gamlME3tkxH58,3252
|
509
512
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=FFBjSWlpKXMxfAUUYUqXbOK_Hd7qBeBsfbcaa9uB4qY,3249
|
513
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
514
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=BrzCCxXtJJHXMmKlo9nm711ZB-yO4uGw4PJLdnY_qqw,11527
|
515
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=zkMzBAqQTSwG9TlGPuwmHV1yN0v5Y_5Hgyo0CKQDVNU,741
|
516
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=On_uvP1ThxgQFAzOWKoteM0vIOHqmtI127A4qbPtmbc,3264
|
510
517
|
sglang/srt/lora/layers.py,sha256=FaTYf0w3zbKKKAT1nJdAzGRtxvySB6FpNKXvEi5RHH0,12958
|
511
518
|
sglang/srt/lora/lora.py,sha256=WY3cISWrQ5Ye3YcNKJUwAWRImzlpLQva2fGepg6P5EY,9744
|
512
519
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
513
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
514
|
-
sglang/srt/lora/mem_pool.py,sha256=
|
520
|
+
sglang/srt/lora/lora_manager.py,sha256=8DG_TJQeHIGXLjSxJt7nFIaEQqgQKjdR4HwbokwDntI,13708
|
521
|
+
sglang/srt/lora/mem_pool.py,sha256=lLmKinsTK3rWTNLJSLSSwKJud98z4up2Lsnb2b5H3ts,10007
|
515
522
|
sglang/srt/lora/utils.py,sha256=3UwpyNONBW8X-ycgDV1lvVD3w_v1mVIs0T2wpVWVe7A,5484
|
516
523
|
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
517
524
|
sglang/srt/lora/backend/flashinfer_backend.py,sha256=el6IAB4kTgDTbwCggmqFuukliyoapN5X6FLksG-4wJ8,4151
|
@@ -521,7 +528,7 @@ sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=vOUDzC_Sq7UGnDbdF8F7ChKG12hD
|
|
521
528
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=qCpJAksCSXS3Znm-ABx1QfrdNqj9hrP61oaeW-n2RhU,5945
|
522
529
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=yNBgl8jS76DPlGJg8puRkSnKkewf2_2oKfVZZRq4lYY,4351
|
523
530
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=EoF9HymgQ1V9DwyOJOvbw1hCbEjprVOne_fC4VHgj-s,4518
|
524
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
531
|
+
sglang/srt/managers/cache_controller.py,sha256=jv2-YkXRc032wnAoTQZMhTUzHrAjqSvdlYOSaWbbHr0,18483
|
525
532
|
sglang/srt/managers/configure_logging.py,sha256=fOJaXAQ1n9m-8KPJndpsKvS885i69SMafoEADLIVfIM,1633
|
526
533
|
sglang/srt/managers/data_parallel_controller.py,sha256=PZ-wOcAFn3PQqMB6I2vjIsFmplf0nlNl5hqTDKTHTG8,12112
|
527
534
|
sglang/srt/managers/detokenizer_manager.py,sha256=SpLxTsSPKBZfD-ZMhJ5zpPPGuUb8PmcYgFSL9CsurU4,10696
|
@@ -529,22 +536,22 @@ sglang/srt/managers/eplb_manager.py,sha256=YaxnvD1-wMV7BhtF9AxoNRVsJUdlQzFF7N-JD
|
|
529
536
|
sglang/srt/managers/expert_distribution.py,sha256=HBcfNdS3l6ob17Z9KFlX5f79rqcaY41XMDp8emMD-TY,30880
|
530
537
|
sglang/srt/managers/expert_location.py,sha256=ZSsH17k5bAgbE1wuvpGaHGueiyhfPrgQakBFPu9jswo,16669
|
531
538
|
sglang/srt/managers/expert_location_dispatch.py,sha256=U6-XLZ77RK0oy_JUVug2q-2LJjwoYX-js0_zhBNMXuM,4148
|
532
|
-
sglang/srt/managers/io_struct.py,sha256=
|
539
|
+
sglang/srt/managers/io_struct.py,sha256=Bpxxn8ht8Q2T7jLEP5M8TK2_Vgn9XPWKvEz6V5yVX_s,33420
|
533
540
|
sglang/srt/managers/mm_utils.py,sha256=mA9W4xZBnXfs-4ZeALvhdpGAYxrJGfOxBWyoHVrt44Q,26518
|
534
541
|
sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
|
535
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
542
|
+
sglang/srt/managers/schedule_batch.py,sha256=2aKod4fNwHayeU9V5M9lFgiY2hliqoeWMPPSauo-Hpo,72438
|
536
543
|
sglang/srt/managers/schedule_policy.py,sha256=6uRRgxbTJ0pztoAg8oRh2u1g6hNejDyMevD2-68zEYA,19723
|
537
|
-
sglang/srt/managers/scheduler.py,sha256=
|
544
|
+
sglang/srt/managers/scheduler.py,sha256=Rq2mVboJha7ce0iGFG6xVjMIn-dyj75QMlIoUnuKf88,104546
|
538
545
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=aaj0z1PD3fGIOPoTtWwqoKsii0yQCR7txVFXMPECveQ,29879
|
539
546
|
sglang/srt/managers/session_controller.py,sha256=Lh1kruMcKqR7WVWYJRZbYgowtsssVlP7_paIVXLLIcE,5756
|
540
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
547
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=NcDNtH_7Bg2QE_v7YmNWDeLcaWFkEn4b-kO7i5KrTM4,65330
|
541
548
|
sglang/srt/managers/tp_worker.py,sha256=cnI2JRxDqM7RXaaXAnLHNyYH4Jt7SB6HLAD5fRoWoNA,10025
|
542
549
|
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=W-FP7dkR9_voS0emMj4N5ML3Iao9gNZc-on6iUflbrw,9835
|
543
550
|
sglang/srt/managers/utils.py,sha256=9_VGE48EK0PXVJ26aYvbRJ6n7gIZALvCcf6uZCccCgM,1369
|
544
551
|
sglang/srt/managers/eplb_algorithms/__init__.py,sha256=wVUv2ZhhC-_VbLaStpk3vulzhqExwfHGZJQqoohs-Fw,1963
|
545
552
|
sglang/srt/managers/eplb_algorithms/deepseek.py,sha256=mMZT7zAAArccdRS0xXxifvMb3qn9enSt426uUTKeiq4,8340
|
546
553
|
sglang/srt/managers/eplb_algorithms/deepseek_vec.py,sha256=Vzy5Iarua1VgVHzjBNZaVV_vt1LY1BLtJz7PmzB701k,10654
|
547
|
-
sglang/srt/managers/multimodal_processors/base_processor.py,sha256
|
554
|
+
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=DQk5qNh7MDY9DQoASiQbCTwRb2HdvLWobzHmE0Ni_fg,21500
|
548
555
|
sglang/srt/managers/multimodal_processors/clip.py,sha256=lRc2mcuDbAhZVf-0EfkO81pqDiol9zLvTpDqtPIBQ2k,1525
|
549
556
|
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=CMfhhdq7u6GzT8ZENo7ByClvQEx-HKaTGVgdYM1vMNw,3460
|
550
557
|
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=oBHXlbwto_84ZkjkW2A7F3Z7kNuDf039uDH4HVXKE1s,2290
|
@@ -558,26 +565,28 @@ sglang/srt/managers/multimodal_processors/mllama4.py,sha256=IAu09ZPMAHxZKsfGiKjZ
|
|
558
565
|
sglang/srt/managers/multimodal_processors/phi4mm.py,sha256=-yTlt2kQkrgks2IzaRKmEj-7siAvTDhZHDR_J3NVFdw,2610
|
559
566
|
sglang/srt/managers/multimodal_processors/pixtral.py,sha256=uQJYbxhafNCmg0xP52FdElnkUatAyintER1XNuKz3b8,4195
|
560
567
|
sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=RLv8sBuKhAjeaVqrFR7hwEEw7fX1WOMZ6r2R4gFeV04,7025
|
568
|
+
sglang/srt/managers/multimodal_processors/vila.py,sha256=AeQlhdIKKoN0lre8_zYQ7YpGu7I_rux1bRLt70sPKJ0,2594
|
561
569
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=WOUIY6ATzltzXQ7QXS9biSY2o_kzbpDIuTD4C6TLCQQ,1019
|
562
|
-
sglang/srt/mem_cache/chunk_cache.py,sha256=
|
570
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=vcA-BI2MwlTiPHrzaufQKg-uYPvpeoizAI4bvv8Ie0w,2045
|
563
571
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
564
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
565
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
572
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=yw-vSz1BBMbjsw90k4i_XAwtlLm6ff-DL0bvEvTbJeg,16671
|
573
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=6qAHD-SLLYbOrJTIqGjgXBE577uwJrFvGknaiBHWzYI,26316
|
574
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=9N34Y7P0aM2xkmhsEw2_W8xN897h-HEwzRPIu1REwac,13186
|
566
575
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=Q-lYcI-3HoLu0WJhE2F_An8g9mkZ8LwMrYnQ4383Rf0,1266
|
567
576
|
sglang/srt/mem_cache/paged_allocator.py,sha256=BrJS0vN1k-vTSgb_M8u_1KoZFRgzgR1WRyImCTq3T0U,9770
|
568
|
-
sglang/srt/mem_cache/radix_cache.py,sha256=
|
577
|
+
sglang/srt/mem_cache/radix_cache.py,sha256=CeDEHnfYONX1Ra5QKemcs06RHzkDa8oV4ZaqHCayGI8,17699
|
569
578
|
sglang/srt/metrics/collector.py,sha256=C9QEJDOEdOPBwy2IJwFS3R6VbGzVzGs2xakKCCPvQDk,19903
|
570
579
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
571
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
580
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=XoChArN7oF-YRApkZwiHHWRY8qFUpFPQ2o3k9K5zuJY,29279
|
572
581
|
sglang/srt/model_executor/expert_location_updater.py,sha256=HWLY5lJAWefy2tobWJKlHs3qlBSCS57EwSMdfUuPFc4,20585
|
573
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
574
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
582
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=zMT-foMHqR51bHZ2qj3KpWjJqDL5cfy7997mhiIFz1E,28848
|
583
|
+
sglang/srt/model_executor/model_runner.py,sha256=1TyEuSOAwr4AMjtutCa2eXijcrK8Pe3-FlmXVcG9xG4,53496
|
575
584
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
576
|
-
sglang/srt/model_loader/loader.py,sha256=
|
585
|
+
sglang/srt/model_loader/loader.py,sha256=JNhJrnCNCXTCroD5FKJdiBr8Dn4VNtTQ0XmqfkPI21k,56002
|
577
586
|
sglang/srt/model_loader/utils.py,sha256=zSZBPA9ErPmkf-HfCxJjhmiFwYueB15KUg7NFspLvPY,4454
|
578
587
|
sglang/srt/model_loader/weight_utils.py,sha256=yKnau-wH9muczoCpDTCVIqXFqz-QJmEEySplX3bMJWk,32153
|
579
588
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
580
|
-
sglang/srt/models/bert.py,sha256=
|
589
|
+
sglang/srt/models/bert.py,sha256=ODJe8YfNRP-hHsomFWk4_QpcuiSsNfjzGf256EDS0Pc,15802
|
581
590
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
582
591
|
sglang/srt/models/clip.py,sha256=mkdSNhc2SgRHyeq9tCLEjUGdnA8yS2EMMbMKSpn5dMs,19863
|
583
592
|
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
@@ -585,7 +594,7 @@ sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,155
|
|
585
594
|
sglang/srt/models/deepseek.py,sha256=ZnN02HdgXCB23Vno5V9UMUoOxH5HC82vNTwsVulUJ-o,17206
|
586
595
|
sglang/srt/models/deepseek_janus_pro.py,sha256=OeeI7vZbE4HGpxa8CwT6-Lbfs7J7WMQ3oBNpVJQpv3w,70450
|
587
596
|
sglang/srt/models/deepseek_nextn.py,sha256=2ziyjv_QEeT3lGNgxG_F-vcAT-K5p2hiz7VEimBgzLc,5675
|
588
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
597
|
+
sglang/srt/models/deepseek_v2.py,sha256=TD9E-60eu7jlEqdW4nT1FQS5x03HzSVxOhhCdGc36nI,85363
|
589
598
|
sglang/srt/models/deepseek_vl2.py,sha256=j8BdxZsMjm6lPdbDipEIKhVIVywCP1Vl1Kl46BZ5_0Y,13147
|
590
599
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
591
600
|
sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
|
@@ -600,7 +609,7 @@ sglang/srt/models/grok.py,sha256=vESZeGS4adI_JAerXIkCcTm15-CNiGeS7VHc36C6w1A,280
|
|
600
609
|
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
601
610
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
602
611
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
603
|
-
sglang/srt/models/internvl.py,sha256=
|
612
|
+
sglang/srt/models/internvl.py,sha256=fZ18eKFYvvtYqoBRXKmS7KlgHMewJSAykADnrf0N3nk,23267
|
604
613
|
sglang/srt/models/kimi_vl.py,sha256=rMJezfEYaEjOaMZ7vt0rg9ZlbV9p1Ax6-kDsVWzf_bI,12868
|
605
614
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
606
615
|
sglang/srt/models/llama.py,sha256=qLBfL77XG3pI-UDxg5HLcgJN1tUMeWNj9-AUR4fUVGg,27144
|
@@ -640,36 +649,37 @@ sglang/srt/models/qwen2_vl.py,sha256=A6YGktXkc9rvotLo0KcZpoUP60eUcFzoiDG65UzXZeI
|
|
640
649
|
sglang/srt/models/qwen3.py,sha256=L-m441pSsduaayMzILrN3isnNqK7jVraUmm_6bEJb1M,14989
|
641
650
|
sglang/srt/models/qwen3_moe.py,sha256=2nOngjhOw93m6nNx0Rc3fM0Yh5lBz_GM1Ri-FCRB-s4,30824
|
642
651
|
sglang/srt/models/registry.py,sha256=bH9H0OiNV0Cn7FRBM30Oh6dxICTs9mJscdLtHYPJvxc,3783
|
643
|
-
sglang/srt/models/roberta.py,sha256=
|
652
|
+
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
644
653
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
645
654
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
646
655
|
sglang/srt/models/torch_native_llama.py,sha256=oTxxof5Wx2b2egIwWx56LeHjtPGQleQ2zM5jXHMiuOU,19293
|
647
656
|
sglang/srt/models/transformers.py,sha256=_CL0npi-_HvqzxkLgFhv2EE3bfGvCLXPYAtPFywZOr0,10260
|
657
|
+
sglang/srt/models/vila.py,sha256=DRGJXP6iSv0XjgHYIJpMzBDNYZb3__Gg_wFkmZ5D66Y,9865
|
648
658
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
649
659
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
650
660
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
651
|
-
sglang/srt/openai_api/adapter.py,sha256=
|
652
|
-
sglang/srt/openai_api/protocol.py,sha256=
|
661
|
+
sglang/srt/openai_api/adapter.py,sha256=OUXKtWrHOIsQly2KtecWo1gdTOzjCMGLHc3IXemgdjg,86874
|
662
|
+
sglang/srt/openai_api/protocol.py,sha256=3PBC8kBhiLaLvbzr0yvuE0CIKCFgnxJQU62t9ADqhVc,16385
|
653
663
|
sglang/srt/openai_api/utils.py,sha256=LL8VB-Qv9kNIVVWG1PYzoKMMHo7Y2NeVLMeJ9QEWVk8,6600
|
654
664
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
655
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
656
|
-
sglang/srt/sampling/sampling_params.py,sha256=
|
665
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=JOGU-Fa8wPtytEJ30BHg1PldeNytwy8u31azLH436kw,13450
|
666
|
+
sglang/srt/sampling/sampling_params.py,sha256=L2cU3MhAo9OvfdEtTdJidp9nTOkD6tiwlegxQ5vgIfU,6127
|
657
667
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
658
668
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
659
669
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
660
670
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
661
671
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
662
|
-
sglang/srt/speculative/build_eagle_tree.py,sha256=
|
663
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=
|
664
|
-
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=
|
665
|
-
sglang/srt/speculative/eagle_utils.py,sha256=
|
666
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
672
|
+
sglang/srt/speculative/build_eagle_tree.py,sha256=lxfaTEOTY0N9QTlgXSUae3DVtPLqW8CcYXWcHsxCJp4,11632
|
673
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=D90K4mTVsHkDYT4izKoAbJoNUzIfSTq5K01TuG8i74o,9038
|
674
|
+
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=qjEH9g0YynGakpfgznTXMm24vEhOROOpy-V6WNY7f60,9836
|
675
|
+
sglang/srt/speculative/eagle_utils.py,sha256=UuyxfbBE9DNL9FPbzyW8Fqt9LLzMq85My5RIrlEny28,42793
|
676
|
+
sglang/srt/speculative/eagle_worker.py,sha256=UOrT2Do9qvmP_gmXeJSzf8sP_sRLbZaBcIfr2cfUydI,35064
|
667
677
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
668
678
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
669
679
|
sglang/test/few_shot_gsm8k.py,sha256=qnEejCyPHGEMBEiNc7T4-t9lvoo2DNN72RXw-ei_TnY,4300
|
670
680
|
sglang/test/few_shot_gsm8k_engine.py,sha256=Yf1Dg0Tk-tY4v1oj_UTxJ7950CWn6kRMbQKDjT2Orgo,3902
|
671
681
|
sglang/test/run_eval.py,sha256=K4Z3OdMPvLeuGJhWWTBD0F-MOUFeBYLvsPnDQ44bd18,4036
|
672
|
-
sglang/test/runners.py,sha256=
|
682
|
+
sglang/test/runners.py,sha256=AOnCXNGO9AYWrUShCDoxYajiN5yVFF9b8fT6XnwAWew,32439
|
673
683
|
sglang/test/send_one.py,sha256=XNZdfZs21tXDBwrDj2pq46WQd5smiKoYETY8U09c1Z8,5079
|
674
684
|
sglang/test/simple_eval_common.py,sha256=OW4Z7O33QqDySRFuHIC4Ouidfup4eaOEuR9i7xJzkDY,12379
|
675
685
|
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
@@ -678,8 +688,9 @@ sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWU
|
|
678
688
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
679
689
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
680
690
|
sglang/test/test_activation.py,sha256=GeTIJHxlLQfW3kM-X1FGa8Sa3dSGKHEXl5wEy-hfGis,1489
|
681
|
-
sglang/test/test_block_fp8.py,sha256=
|
682
|
-
sglang/test/
|
691
|
+
sglang/test/test_block_fp8.py,sha256=1qBD-FJr5UaR9e5qDz91vDrS_DT1utnk82qeQ2bm-1E,21630
|
692
|
+
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7Xx0MjOoOBYL8J7ETvOVA,8180
|
693
|
+
sglang/test/test_block_fp8_ep.py,sha256=TI0TVeoX8zRDtOFclonCfgSH6vnAIOGiMKQKpf9aKNs,10845
|
683
694
|
sglang/test/test_custom_ops.py,sha256=2bSo9P5_rJZYFq8Y8IKRimDfFyZZGJluhL7Ngny0Pf4,5571
|
684
695
|
sglang/test/test_cutlass_moe.py,sha256=beXdvpwpHh0O8fpLW-RV3Bx8Wu0lRFG_SNkL3Op5ITA,9905
|
685
696
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
@@ -687,13 +698,13 @@ sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsu
|
|
687
698
|
sglang/test/test_fp4_moe.py,sha256=U4LHzpGl6pCiCZiENRPxVP6hxqkqRZ_0WXbB29vYeAo,8187
|
688
699
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
689
700
|
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
690
|
-
sglang/test/test_utils.py,sha256=
|
701
|
+
sglang/test/test_utils.py,sha256=xdi1-Fvs0ykmaYhYzC0Jx-n7nSFKSO9a6HAvWbXqVQo,36176
|
691
702
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
692
703
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
693
704
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
694
|
-
sglang/test/attention/test_prefix_chunk_info.py,sha256=
|
695
|
-
sglang-0.4.7.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
696
|
-
sglang-0.4.7.dist-info/METADATA,sha256=
|
697
|
-
sglang-0.4.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
698
|
-
sglang-0.4.7.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
699
|
-
sglang-0.4.7.dist-info/RECORD,,
|
705
|
+
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
706
|
+
sglang-0.4.7.post1.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
707
|
+
sglang-0.4.7.post1.dist-info/METADATA,sha256=DgH_mVdir5t4SV58Js1jZLSeJ5qB4bH0FW7aO3RfR20,26966
|
708
|
+
sglang-0.4.7.post1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
709
|
+
sglang-0.4.7.post1.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
710
|
+
sglang-0.4.7.post1.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|