sglang 0.5.1__py3-none-any.whl → 0.5.1.post2__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/srt/disaggregation/decode.py +4 -0
- sglang/srt/disaggregation/prefill.py +4 -0
- sglang/srt/entrypoints/engine.py +1 -1
- sglang/srt/entrypoints/tool.py +7 -7
- sglang/srt/layers/attention/flashinfer_mla_backend.py +71 -89
- sglang/srt/layers/attention/utils.py +15 -94
- sglang/srt/layers/moe/cutlass_moe.py +0 -7
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py +6 -2
- sglang/srt/layers/quantization/modelopt_quant.py +2 -2
- sglang/srt/lora/lora_manager.py +29 -12
- sglang/srt/managers/scheduler_metrics_mixin.py +15 -0
- sglang/srt/metrics/collector.py +5 -5
- sglang/srt/model_executor/cuda_graph_runner.py +2 -2
- sglang/srt/models/grok.py +0 -4
- sglang/srt/offloader.py +115 -0
- sglang/srt/server_args.py +0 -4
- sglang/srt/utils.py +0 -7
- sglang/test/test_cutlass_moe.py +33 -28
- sglang/version.py +1 -1
- {sglang-0.5.1.dist-info → sglang-0.5.1.post2.dist-info}/METADATA +4 -4
- {sglang-0.5.1.dist-info → sglang-0.5.1.post2.dist-info}/RECORD +25 -24
- {sglang-0.5.1.dist-info → sglang-0.5.1.post2.dist-info}/WHEEL +0 -0
- {sglang-0.5.1.dist-info → sglang-0.5.1.post2.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.5.1.dist-info → sglang-0.5.1.post2.dist-info}/top_level.txt +0 -0
@@ -9,7 +9,7 @@ sglang/global_config.py,sha256=ZMTux_PsGnvkyJ0kTFwhTdbnFwIjjpGDogut_9Lu4Vo,1732
|
|
9
9
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
10
10
|
sglang/profiler.py,sha256=tEHzHerXC-ymk4OrkoUcMbgcGHmb8VESthsNSP2Yx9w,4417
|
11
11
|
sglang/utils.py,sha256=dC2PNkKYTgDHsNrWdZJ74GvaXGSHCeIk_aZ-TA89OhY,16380
|
12
|
-
sglang/version.py,sha256=
|
12
|
+
sglang/version.py,sha256=NzwicjWvX-oujWpkElhba_Uhu9tnA3prazJglxgYyRM,28
|
13
13
|
sglang/eval/llama3_eval.py,sha256=mLNRZJIqV4CfqrY8UGnJEcHw2Xsyr1eyYZgFSUFYr1g,9997
|
14
14
|
sglang/eval/loogle_eval.py,sha256=-CC2s2kh5qUoDrHRkQVkC_jNvBgNojXbf456ny5s78s,4557
|
15
15
|
sglang/lang/api.py,sha256=rcp3GeoyZhmJ0GDLPRkuZNcxd0TBJy_wfUDpcmQoqW8,7210
|
@@ -36,16 +36,16 @@ sglang/srt/hf_transformers_utils.py,sha256=WgpIr56YuKG8Hmp_vrZBfePYWMzDPVhH8k0p4
|
|
36
36
|
sglang/srt/host_shared_memory.py,sha256=00TgVm3PNCl4rTPJZChG5uu4I5hd_Xf587r39tibmIg,2274
|
37
37
|
sglang/srt/jinja_template_utils.py,sha256=XCuqi6iHQrtziUvhy22ePdh8WcS42O9sKxuXpM_bMXc,7836
|
38
38
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
39
|
-
sglang/srt/offloader.py,sha256=
|
39
|
+
sglang/srt/offloader.py,sha256=iu6Q5lOzJvuQVmq_CEYWitu41sNF1wmavTvOxlyEGaU,18097
|
40
40
|
sglang/srt/operations.py,sha256=za_h1_kcR1Te6-i_r0i_zAeumbmIRhLK2pS31sukkrw,6089
|
41
41
|
sglang/srt/operations_strategy.py,sha256=-w6GI2VgSGvORy3pUWRAJo6244ykSW1ZBV1Dx0fZlHA,7138
|
42
42
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
43
43
|
sglang/srt/poll_based_barrier.py,sha256=9vjn32ROlSueEk7EuZjWKUrrL7XVR9KJsSVliGTYB_4,937
|
44
44
|
sglang/srt/reasoning_parser.py,sha256=er9PSDKroGhXG52k0Kz9Aw5o_7rpN1LXVp5mmZgtzqY,22948
|
45
|
-
sglang/srt/server_args.py,sha256
|
45
|
+
sglang/srt/server_args.py,sha256=5IjWQay7BuqKtdt9LzpFXb24jo1ncqW3tVZ-7ho3GoY,102200
|
46
46
|
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
47
47
|
sglang/srt/two_batch_overlap.py,sha256=UykF5nC2rja3Hvmu0D9glqKdVRIEhQGPV84Jm7veopQ,34150
|
48
|
-
sglang/srt/utils.py,sha256=
|
48
|
+
sglang/srt/utils.py,sha256=7fxz77imEmlHWgYvvl5JrmjmwYOT6pLhlWx97MSWioA,93243
|
49
49
|
sglang/srt/warmup.py,sha256=zldxhMlXpclRAJXmfBjJNUJd1eDizVdysibBvQyTVuA,1782
|
50
50
|
sglang/srt/configs/__init__.py,sha256=gas3cKYVgZp7qF4m8FejX4EUUmdQd_w5WDTm7fo7yM0,743
|
51
51
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
@@ -81,12 +81,12 @@ sglang/srt/debug_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3
|
|
81
81
|
sglang/srt/debug_utils/dump_comparator.py,sha256=8ZPwP0zojfRHvPiSKgpESYFcC3tR-sBjIej5SotOmpg,3947
|
82
82
|
sglang/srt/debug_utils/dumper.py,sha256=eyrg5lmwyYF88kn8b06kpu1__aGnWb6CLM8fxywtooI,3158
|
83
83
|
sglang/srt/debug_utils/text_comparator.py,sha256=pg58q3fzsnd3rJKRgZTdcOviOtAv8pSYZdwf-TLffMM,5522
|
84
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
84
|
+
sglang/srt/disaggregation/decode.py,sha256=EELA3krHp4YtRIpUYU0-9LSFd7XQuvKn3yiHGrK7gaI,34598
|
85
85
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=Iu7ehHGAfYIVATtClwX6y-6zxWs-JyDlMotYo_5yuUc,6598
|
86
86
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
87
87
|
sglang/srt/disaggregation/launch_lb.py,sha256=pmHwo1GWbpHZn4IDKnOEHYVcfdKpsYuTHUMowNo3TrE,3891
|
88
88
|
sglang/srt/disaggregation/mini_lb.py,sha256=4l3W2COZuX8DbLg8AQvAhv5EncH9FkEv2HF5fhn3GQM,14630
|
89
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
89
|
+
sglang/srt/disaggregation/prefill.py,sha256=CLoixMP1qRWO-VEsvVbjfQOu4ggqF0KeuHhxZC-NSvU,36272
|
90
90
|
sglang/srt/disaggregation/utils.py,sha256=evdv4AkQxJzTqdO0jrdAr7vHUbBSCEXMzNREh0FoRLc,12294
|
91
91
|
sglang/srt/disaggregation/ascend/__init__.py,sha256=-lxnica6fZYmYNpKwmE8yESUpQ5Sxf2DiZoBHzboKc8,146
|
92
92
|
sglang/srt/disaggregation/ascend/conn.py,sha256=oBhEQ83SbIlYc7QSG6Cqk48QqdYSlxcSMWbc-2KXlXM,1191
|
@@ -122,11 +122,11 @@ sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=IrSrnpZnii0E
|
|
122
122
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
123
123
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
124
124
|
sglang/srt/entrypoints/context.py,sha256=aD-94xkD0komuGO5gtYUoJKCHdc4hAipMxQt04yVRGA,8030
|
125
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
125
|
+
sglang/srt/entrypoints/engine.py,sha256=SrN5nGG9oWZJvXHW3W17hNxpdKN7GH__08in0o4KX_s,33151
|
126
126
|
sglang/srt/entrypoints/harmony_utils.py,sha256=01T-A5GBUm2b306PcxNEg2rfx4cykBcqNYrzcXTWBlc,13590
|
127
127
|
sglang/srt/entrypoints/http_server.py,sha256=B_nV6dqQWOHj2t_r0_rip30AMfJ8ZTgnIUJLeVt3qQw,44249
|
128
128
|
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
129
|
-
sglang/srt/entrypoints/tool.py,sha256=
|
129
|
+
sglang/srt/entrypoints/tool.py,sha256=aAXEjBqkr5j6_IgRL8fZCKgoDPY2TikM20-LQXU9TaI,2709
|
130
130
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
131
131
|
sglang/srt/entrypoints/openai/protocol.py,sha256=S_uMVVg8LwxN__O6corf60VqayNQMAGM_BxxU916RGE,26499
|
132
132
|
sglang/srt/entrypoints/openai/serving_base.py,sha256=epD6J7K72p6TP8o2dGYf-a76nXeF80vFhPRpWts6684,5445
|
@@ -191,7 +191,7 @@ sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQze
|
|
191
191
|
sglang/srt/layers/attention/dual_chunk_flashattention_backend.py,sha256=hCATQEhBATZpPhBMF-cCM9r6nxXA0dr3jOT_hTFS_T0,68656
|
192
192
|
sglang/srt/layers/attention/flashattention_backend.py,sha256=bB4lW2TqTr-j0TOk1nxOnCytRVtAksRECxqIRKx-VKQ,94851
|
193
193
|
sglang/srt/layers/attention/flashinfer_backend.py,sha256=J5Q5PeMyMo0NZa2BLgVWJZHST4UQCrifP6Rrv7iXlXc,54215
|
194
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
194
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=JUGO2jP0QgiIr39DqcO8ApYgVSPEq5UDQzbcSDMXys0,39574
|
195
195
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=5iSic5ho-lkXNas9mR3uLbXbEl-do31gc8gjR7-a79k,20711
|
196
196
|
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=dwbxscTGMOnwfxxPpmGdbSiQ0kQRHnH0pdpKHA-_vqc,3181
|
197
197
|
sglang/srt/layers/attention/intel_amx_backend.py,sha256=hH9lxXs_o66_IVs58oPhRCOXGUrHbXSz82FKtHr9GO8,4092
|
@@ -201,7 +201,7 @@ sglang/srt/layers/attention/torch_native_backend.py,sha256=RsI4lYiQJAj-Xy0vKkzby
|
|
201
201
|
sglang/srt/layers/attention/triton_backend.py,sha256=fvcJLaJaM8JE9Q9Nkmn0dzdYnnYlwELCoxQGMoqS9Gk,41858
|
202
202
|
sglang/srt/layers/attention/trtllm_mha_backend.py,sha256=8MxCAzqsNuvO3mhFqTMXCJ0Tt0_82kFbBHie6m0ieDA,27588
|
203
203
|
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=pkXARtA9ISC3RL82mqjY7vzfsK-u1rvMRBcOn2n0J_o,19101
|
204
|
-
sglang/srt/layers/attention/utils.py,sha256=
|
204
|
+
sglang/srt/layers/attention/utils.py,sha256=lx_jNw2VwlBe2VnDb1eXRRdN9WArw9rdWHTHqndUEFk,3174
|
205
205
|
sglang/srt/layers/attention/vision.py,sha256=PZUJuswPWvJ34NTtxJkcXnusojDv0pO0UhrsjL4SWYU,20268
|
206
206
|
sglang/srt/layers/attention/vision_utils.py,sha256=6hPPAt8p3SOm7tgHNUesnMLxvQiKbaOM5EK6K-ig5dI,2771
|
207
207
|
sglang/srt/layers/attention/wave_backend.py,sha256=_rjyALSl5huNtIGSe6OJlBrC04LhwBBu62bgjlkavkw,23010
|
@@ -215,7 +215,7 @@ sglang/srt/layers/attention/wave_ops/decode_attention.py,sha256=C-W1hvswZ7ggDKp4
|
|
215
215
|
sglang/srt/layers/attention/wave_ops/extend_attention.py,sha256=aPNVsrhJD3OW7YF3jRm59IIawgA-bv_6GT91UPf5x5Y,3957
|
216
216
|
sglang/srt/layers/attention/wave_ops/prefill_attention.py,sha256=viTUit0rxjVV5UahuwmVAhmL66YRFJD4g1YhH_oRBu8,2344
|
217
217
|
sglang/srt/layers/moe/__init__.py,sha256=63TxUpSiUpVg1SDY1zdlTg3WFJzAc7WSndOViOmUv4E,835
|
218
|
-
sglang/srt/layers/moe/cutlass_moe.py,sha256=
|
218
|
+
sglang/srt/layers/moe/cutlass_moe.py,sha256=jCstMBsBTZZ_SyQyzw_IaHVFcYkvVouQImt03GYyFTI,14511
|
219
219
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
220
220
|
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=rWyHMg0kYZhIdLWTJeC7pqRG9ywfeKqi47-OekNeF4Y,7306
|
221
221
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=8SAToE4B-22H5JsENZgJ1Io6QfE5-D9ItWLtbGksFQQ,3372
|
@@ -418,6 +418,7 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
418
418
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Max-Q_Workstation_Edition,dtype=fp8_w8a8.json",sha256=RMYwqtB7hYeaCyuZ1feVnRhBGlN4jMcmNQX2hqUqBlk,3254
|
419
419
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=W8C1GtP4K43SK9128U52DD5WWofvPleAJE4us2Qju1k,3251
|
420
420
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=161,N=384,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Max-Q_Workstation_Edition,dtype=fp8_w8a8.json",sha256=RMYwqtB7hYeaCyuZ1feVnRhBGlN4jMcmNQX2hqUqBlk,3254
|
421
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=T6kCtCUytCxiW8JOLfEF3YgdCD9_mKccJ85IqT0b8LU,3253
|
421
422
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=FEnjuvvky-cvW1iq8TPrfGOOH8y4rOEx4jlYZ4tqbDs,3253
|
422
423
|
sglang/srt/layers/moe/moe_runner/__init__.py,sha256=piJQmSz7BOBaxVd0gGMgRLzaD21r7PH1NEDOK5hktYk,97
|
423
424
|
sglang/srt/layers/moe/moe_runner/base.py,sha256=L7ZNcq6fQxMXQZypcxWKIe1j9ajoOKCsFRrF-UlHVaA,364
|
@@ -440,7 +441,7 @@ sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V
|
|
440
441
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
441
442
|
sglang/srt/layers/quantization/marlin_utils.py,sha256=aM3GU7b7rHNZE-tZjRSrtOaPWzSaMcLxck4he8MlEVI,26344
|
442
443
|
sglang/srt/layers/quantization/marlin_utils_fp8.py,sha256=iSjq-ikPOTU5plrWNTW4MletKLySIrNl5NhQmY6FyAo,12508
|
443
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
444
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=k0F6b-bG5wv3zL7kipqCrQHEZ8QjfIDThnU9Y3mFNTA,52566
|
444
445
|
sglang/srt/layers/quantization/moe_wna16.py,sha256=brU0nG6StgjGuuhOjpeoh-wJVZ1SUgbuHhiDR1hibbw,18905
|
445
446
|
sglang/srt/layers/quantization/mxfp4.py,sha256=v6GlGpvJT2GH75djiJHmz4r-E3SKhvpVD_-UJrHKfUM,31410
|
446
447
|
sglang/srt/layers/quantization/mxfp4_tensor.py,sha256=I1hh_uZqIqkgFnNyjaP17cDMLMV5rs3aFytg91MPhzk,5357
|
@@ -614,7 +615,7 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
614
615
|
"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
|
615
616
|
sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
616
617
|
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=FaHKgY9y1oi3zlCmkorSK4r4dhPy7NiviVIhtabvzjM,11536
|
617
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=
|
618
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=LPO728y32uHQOGfk8U26jDIbGlAcQdD-ZYaqfboyhzM,853
|
618
619
|
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=On_uvP1ThxgQFAzOWKoteM0vIOHqmtI127A4qbPtmbc,3264
|
619
620
|
sglang/srt/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
620
621
|
sglang/srt/layers/quantization/quark/quark.py,sha256=EqQvWzAc6nd_yl6UIMIwmozKif4I8fRNfBum040UUEQ,14613
|
@@ -626,7 +627,7 @@ sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=gMKmrpim
|
|
626
627
|
sglang/srt/lora/layers.py,sha256=3RwD5TC4zO8A2Haz7ScIT5vc_neU9RHM3DoamKttVkw,10838
|
627
628
|
sglang/srt/lora/lora.py,sha256=lPPEJavrfANXDzdmKEg4hbgmKIiEr3NU7KNJeaaKTB8,7393
|
628
629
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
629
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
630
|
+
sglang/srt/lora/lora_manager.py,sha256=HSA-ZnL2NUytos4DxzawrZ-1yoaoL42Stn5Y92lXf7w,21781
|
630
631
|
sglang/srt/lora/lora_registry.py,sha256=osbau-sQZ7BuCeGGpBMFy4w40GO5FGqRgRwDyxxgNmg,8167
|
631
632
|
sglang/srt/lora/mem_pool.py,sha256=FDf9qNEWrZ3yTtrUEvbiUN9FUawRZBlK9l9A2ou5dkU,11242
|
632
633
|
sglang/srt/lora/utils.py,sha256=DePsHi-0S-eCerQeWXTW9U7sG2397w_Bhfs0TAsu4xk,3904
|
@@ -648,7 +649,7 @@ sglang/srt/managers/schedule_batch.py,sha256=9lhBnf-siQjsThD8FRyhiF50N-LOE7dfoPr
|
|
648
649
|
sglang/srt/managers/schedule_policy.py,sha256=vh9BQW9tBv80LW4JApLE6smU2m4gy6cAEI25HVXiS60,22383
|
649
650
|
sglang/srt/managers/scheduler.py,sha256=RXVUuOLyboWV9NR9U12EhfcJeKfW34fVLFmZGd4OFNA,107583
|
650
651
|
sglang/srt/managers/scheduler_input_blocker.py,sha256=zP8xU_UmU2H0AB6sEqvivDcDB1QDgTauNDYDIJ7Nez4,3683
|
651
|
-
sglang/srt/managers/scheduler_metrics_mixin.py,sha256
|
652
|
+
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=31BbukSyUUPMNHLqRlS5sEiAv7Gi5VHFQ1TgxvcAdcw,10054
|
652
653
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=e_l5TRm05liINSAeZU-YPRpJXcutmEWYV30F1vPaxbs,31345
|
653
654
|
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=A67lC_U7HUCf_znatXK51orC8xeFNGouJ866HH_Y-yc,11402
|
654
655
|
sglang/srt/managers/scheduler_recv_skipper.py,sha256=8rVQCBjn9f26Th4XbeUS3fEsvo1GI029Me28wMjcKRY,1103
|
@@ -684,9 +685,9 @@ sglang/srt/mem_cache/storage/mooncake_store/unit_test.py,sha256=jMdJgU41VscKS-mn
|
|
684
685
|
sglang/srt/mem_cache/storage/nixl/hicache_nixl.py,sha256=bau9Jsp50lpEiy_osgb-dYzeoUkPWM03x7Q8z2BpKaU,9920
|
685
686
|
sglang/srt/mem_cache/storage/nixl/nixl_utils.py,sha256=KXkwMrbWwIOUOASINnUo4HyheiMd-93smmwGLv0CacU,7463
|
686
687
|
sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py,sha256=vENVvGAd3PqcQEFA812wPoSBYhRemLr8Sfh1LQa0INU,9609
|
687
|
-
sglang/srt/metrics/collector.py,sha256=
|
688
|
+
sglang/srt/metrics/collector.py,sha256=IfFr4RaamT3TPj9DjuEnvkdiBGKcIUCQSIIwd9GeZe0,20295
|
688
689
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
689
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
690
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=fZT_CQwhfu7kdnliKu5lYM2tunU0u3wBoIlCxm4FXCA,33920
|
690
691
|
sglang/srt/model_executor/forward_batch_info.py,sha256=2KBu9SChR-YwSNbw1mO3WR0P_EGQjFUC5rQfBx6js90,40707
|
691
692
|
sglang/srt/model_executor/model_runner.py,sha256=FJYnyFsy6UqX3ZTZQZz0alyVGj8zs9IlSmQn9AfNAj0,78564
|
692
693
|
sglang/srt/model_executor/npu_graph_runner.py,sha256=isp2Plkf4b_gdjptYxJhTJk7JL21Jg-Md3hAYIuSVxM,3424
|
@@ -728,7 +729,7 @@ sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtY
|
|
728
729
|
sglang/srt/models/gpt_oss.py,sha256=qXa6BAm8gBTuCSX0ax3Iz4SkIIko0s1u8sVu8kJVzkY,44930
|
729
730
|
sglang/srt/models/granite.py,sha256=8q92shxVPAp_cJDohJATffSGd7Z0Oi-vF5jpY6DlK4s,19840
|
730
731
|
sglang/srt/models/granitemoe.py,sha256=j1rgZ62CbBioECjUblDCw_NneDQgY_QJODsI0fqXVO8,13779
|
731
|
-
sglang/srt/models/grok.py,sha256=
|
732
|
+
sglang/srt/models/grok.py,sha256=8KCR13LtdnhswJrIwgb0sdFW0OxCA8GQ0fbN8gb856E,40518
|
732
733
|
sglang/srt/models/hunyuan.py,sha256=RSZErx-Swt65kmfvSXJQJJ6KhjucuNY4UUVLWC8hWaA,31102
|
733
734
|
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
734
735
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
@@ -847,7 +848,7 @@ sglang/test/test_block_fp8.py,sha256=mOM-eX9LisotPlMLSCvH4XwWMbvNpVOBtt7euXuVTDw
|
|
847
848
|
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7Xx0MjOoOBYL8J7ETvOVA,8180
|
848
849
|
sglang/test/test_block_fp8_ep.py,sha256=n4X6ZKwuUUbV5Ofjg64ptlaFGI1LbRXDfFiJW1ELHgY,10546
|
849
850
|
sglang/test/test_custom_ops.py,sha256=PenQ8zM1wj5xwiVEPVzD37pO-x90aOfFMpCRZenaKsY,5709
|
850
|
-
sglang/test/test_cutlass_moe.py,sha256=
|
851
|
+
sglang/test/test_cutlass_moe.py,sha256=ax-IYPm5tZjkZft0q8swHnzerOI4LB4JOLFaKGJVE-k,9629
|
851
852
|
sglang/test/test_cutlass_w4a8_moe.py,sha256=E0ffQOR84bEFz6KFNbczH2LRhQqkeC9HPp76u0vzdwo,8809
|
852
853
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
853
854
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
@@ -862,8 +863,8 @@ sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqn
|
|
862
863
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
863
864
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
864
865
|
sglang/test/attention/test_trtllm_mla_backend.py,sha256=ilrX20-1hVo0nmKN0GTqzKoUmDarTXGS8nWJ6c8RHVY,41792
|
865
|
-
sglang-0.5.1.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
866
|
-
sglang-0.5.1.dist-info/METADATA,sha256=
|
867
|
-
sglang-0.5.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
868
|
-
sglang-0.5.1.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
869
|
-
sglang-0.5.1.dist-info/RECORD,,
|
866
|
+
sglang-0.5.1.post2.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
867
|
+
sglang-0.5.1.post2.dist-info/METADATA,sha256=9Ogyh9spoioHR_Xp-c2t_ZomDJPn6sc26KEYpjYIWAA,27803
|
868
|
+
sglang-0.5.1.post2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
869
|
+
sglang-0.5.1.post2.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
870
|
+
sglang-0.5.1.post2.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|