sglang 0.5.2rc0__py3-none-any.whl → 0.5.2rc2__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/lang/interpreter.py +1 -1
- sglang/srt/configs/internvl.py +6 -0
- sglang/srt/configs/model_config.py +2 -1
- sglang/srt/disaggregation/mini_lb.py +2 -2
- sglang/srt/distributed/parallel_state.py +46 -41
- sglang/srt/entrypoints/engine.py +1 -1
- sglang/srt/entrypoints/http_server.py +5 -1
- sglang/srt/entrypoints/openai/protocol.py +3 -3
- sglang/srt/entrypoints/openai/serving_chat.py +3 -3
- sglang/srt/entrypoints/openai/serving_completions.py +3 -1
- sglang/srt/entrypoints/openai/serving_embedding.py +1 -1
- sglang/srt/entrypoints/openai/serving_responses.py +1 -1
- sglang/srt/function_call/gpt_oss_detector.py +1 -1
- sglang/srt/layers/attention/aiter_backend.py +93 -68
- sglang/srt/layers/communicator.py +45 -7
- sglang/srt/layers/moe/cutlass_w4a8_moe.py +1 -9
- sglang/srt/layers/moe/ep_moe/layer.py +2 -7
- sglang/srt/layers/moe/fused_moe_triton/__init__.py +5 -3
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,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 +5 -1048
- sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py +212 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py +796 -0
- sglang/srt/layers/moe/fused_moe_triton/layer.py +5 -2
- sglang/srt/layers/moe/fused_moe_triton/moe_align_block_size.py +87 -0
- sglang/srt/layers/moe/utils.py +0 -1
- sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py +8 -0
- sglang/srt/layers/quantization/modelopt_quant.py +35 -2
- sglang/srt/layers/quantization/mxfp4.py +4 -1
- sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py +49 -30
- sglang/srt/layers/quantization/quark/utils.py +97 -0
- sglang/srt/layers/quantization/rocm_mxfp4_utils.py +13 -0
- sglang/srt/layers/quantization/w4afp8.py +30 -25
- sglang/srt/layers/rocm_linear_utils.py +44 -0
- sglang/srt/layers/rotary_embedding.py +0 -18
- sglang/srt/managers/cache_controller.py +42 -39
- sglang/srt/managers/detokenizer_manager.py +0 -34
- sglang/srt/managers/multi_tokenizer_mixin.py +48 -6
- sglang/srt/managers/schedule_policy.py +3 -2
- sglang/srt/managers/scheduler.py +7 -100
- sglang/srt/managers/scheduler_metrics_mixin.py +113 -7
- sglang/srt/managers/template_manager.py +3 -3
- sglang/srt/managers/tokenizer_manager.py +1 -0
- sglang/srt/mem_cache/allocator.py +1 -1
- sglang/srt/mem_cache/hicache_storage.py +15 -10
- sglang/srt/mem_cache/hiradix_cache.py +16 -0
- sglang/srt/mem_cache/memory_pool_host.py +18 -11
- sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py +61 -34
- sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py +35 -6
- sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py +32 -13
- sglang/srt/mem_cache/storage/mooncake_store/test_mooncake_store.py +161 -0
- sglang/srt/metrics/collector.py +12 -4
- sglang/srt/metrics/utils.py +48 -0
- sglang/srt/model_executor/forward_batch_info.py +16 -17
- sglang/srt/model_executor/model_runner.py +1 -1
- sglang/srt/models/deepseek_v2.py +245 -36
- sglang/srt/models/glm4_moe.py +10 -1
- sglang/srt/models/gpt_oss.py +5 -4
- sglang/srt/models/internvl.py +28 -0
- sglang/srt/models/longcat_flash.py +26 -15
- sglang/srt/models/longcat_flash_nextn.py +23 -15
- sglang/srt/models/minicpmv.py +165 -3
- sglang/srt/models/qwen2_moe.py +4 -1
- sglang/srt/models/qwen3.py +8 -2
- sglang/srt/models/qwen3_moe.py +39 -8
- sglang/srt/models/torch_native_llama.py +1 -1
- sglang/srt/{reasoning_parser.py → parser/reasoning_parser.py} +1 -1
- sglang/srt/server_args.py +79 -2
- sglang/srt/speculative/eagle_worker.py +158 -112
- sglang/srt/utils.py +12 -10
- sglang/test/few_shot_gsm8k.py +1 -0
- sglang/test/test_cutlass_w4a8_moe.py +24 -9
- sglang/utils.py +1 -0
- sglang/version.py +1 -1
- {sglang-0.5.2rc0.dist-info → sglang-0.5.2rc2.dist-info}/METADATA +2 -2
- {sglang-0.5.2rc0.dist-info → sglang-0.5.2rc2.dist-info}/RECORD +83 -76
- sglang/srt/mem_cache/storage/mooncake_store/unit_test.py +0 -40
- /sglang/srt/{model_parallel.py → layers/model_parallel.py} +0 -0
- /sglang/srt/{code_completion_parser.py → parser/code_completion_parser.py} +0 -0
- /sglang/srt/{conversation.py → parser/conversation.py} +0 -0
- /sglang/srt/{harmony_parser.py → parser/harmony_parser.py} +0 -0
- /sglang/srt/{jinja_template_utils.py → parser/jinja_template_utils.py} +0 -0
- {sglang-0.5.2rc0.dist-info → sglang-0.5.2rc2.dist-info}/WHEEL +0 -0
- {sglang-0.5.2rc0.dist-info → sglang-0.5.2rc2.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.5.2rc0.dist-info → sglang-0.5.2rc2.dist-info}/top_level.txt +0 -0
@@ -8,15 +8,15 @@ sglang/compile_deep_gemm.py,sha256=EsgboGA-MK3Rvx9TlUJPLxJ5LBira4bTcHJLKEp1H6k,6
|
|
8
8
|
sglang/global_config.py,sha256=ZMTux_PsGnvkyJ0kTFwhTdbnFwIjjpGDogut_9Lu4Vo,1732
|
9
9
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
10
10
|
sglang/profiler.py,sha256=JCpZzlDhahoiPlPi5IG3n7GFrQHxfHEB6ELie3Ck55w,4397
|
11
|
-
sglang/utils.py,sha256=
|
12
|
-
sglang/version.py,sha256=
|
11
|
+
sglang/utils.py,sha256=kFNoD3nZlxrKmE_wXH-yEx5gN9FL0mq8jPsCBigwvV4,16505
|
12
|
+
sglang/version.py,sha256=HtG3pxmhM9RrybwJX4CHS2qdHTEHVYggcuJtZGJa478,25
|
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
|
16
16
|
sglang/lang/chat_template.py,sha256=4_JVa7NDpHP2it6rAQS5UnCSxSMy0rtfdOgSvH_Kbdc,22549
|
17
17
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
18
18
|
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
19
|
-
sglang/lang/interpreter.py,sha256=
|
19
|
+
sglang/lang/interpreter.py,sha256=F-wxyKDUnTygmJpSEYsrQermls2RyWJntOep9_P7V1I,34818
|
20
20
|
sglang/lang/ir.py,sha256=FnRJ-lndAsR4GR0ONJRPDtlYx8FvL9RIk44vSA16RBk,19656
|
21
21
|
sglang/lang/tracer.py,sha256=ljBo9VZ0zVaGwzNk32qw21acyo60N0UjIjqBbT5a1WI,8175
|
22
22
|
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
@@ -28,25 +28,19 @@ sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZ
|
|
28
28
|
sglang/srt/_custom_ops.py,sha256=9GPNUyqnybgvUnzdQ8n5_NgluHmQNw0Gptos0iLPfrY,5342
|
29
29
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
30
30
|
sglang/srt/bench_utils.py,sha256=zNTsTBUta27XxojgvR5p5X9M0v1MFzZ7dcX9TMq4NvQ,4348
|
31
|
-
sglang/srt/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
32
31
|
sglang/srt/constants.py,sha256=0i-tEwG2BSYNDy96MxnGHV5HnBELkYcnsVGsE-R18o0,93
|
33
|
-
sglang/srt/conversation.py,sha256=cmVT4SCqRYxprYvmftUC_z_TkhXCqYC9B2rVZsmQe30,38869
|
34
32
|
sglang/srt/custom_op.py,sha256=7OPQAZe3PqDXk-xM0Wxl7pm9cazilNJfkNiYIWztWgI,3198
|
35
|
-
sglang/srt/harmony_parser.py,sha256=YweG4azWm5jmzYGaAHEXSaORpgWctPpSGQk_jp5H-CE,23227
|
36
33
|
sglang/srt/hf_transformers_utils.py,sha256=XifKc8JTPr_CkQtdLZ5-OvsNzapGgny_JJSIkYaiJYo,15674
|
37
34
|
sglang/srt/host_shared_memory.py,sha256=00TgVm3PNCl4rTPJZChG5uu4I5hd_Xf587r39tibmIg,2274
|
38
|
-
sglang/srt/jinja_template_utils.py,sha256=XCuqi6iHQrtziUvhy22ePdh8WcS42O9sKxuXpM_bMXc,7836
|
39
|
-
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
40
35
|
sglang/srt/offloader.py,sha256=iu6Q5lOzJvuQVmq_CEYWitu41sNF1wmavTvOxlyEGaU,18097
|
41
36
|
sglang/srt/operations.py,sha256=za_h1_kcR1Te6-i_r0i_zAeumbmIRhLK2pS31sukkrw,6089
|
42
37
|
sglang/srt/operations_strategy.py,sha256=-w6GI2VgSGvORy3pUWRAJo6244ykSW1ZBV1Dx0fZlHA,7138
|
43
38
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
44
39
|
sglang/srt/poll_based_barrier.py,sha256=9vjn32ROlSueEk7EuZjWKUrrL7XVR9KJsSVliGTYB_4,937
|
45
|
-
sglang/srt/
|
46
|
-
sglang/srt/server_args.py,sha256=qEh8ykOglDMHh3GvyUhG0oOSJq_tH8vUYtDzSukoOtk,104043
|
40
|
+
sglang/srt/server_args.py,sha256=-p0yxNLdbHGFmW1PfC-Dhhg2Y9Yw--lCD3Vwv-t3r6E,107575
|
47
41
|
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
48
42
|
sglang/srt/two_batch_overlap.py,sha256=UykF5nC2rja3Hvmu0D9glqKdVRIEhQGPV84Jm7veopQ,34150
|
49
|
-
sglang/srt/utils.py,sha256=
|
43
|
+
sglang/srt/utils.py,sha256=QVuZIlNYroA6Upso2-SiqGuTnN--BbzCdw-YReZwGWs,95559
|
50
44
|
sglang/srt/warmup.py,sha256=zldxhMlXpclRAJXmfBjJNUJd1eDizVdysibBvQyTVuA,1782
|
51
45
|
sglang/srt/configs/__init__.py,sha256=3GdmJ2DUiNq1zNs3yOILwZzL0J8fK-h8k2P5YVgxEI0,833
|
52
46
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
@@ -54,13 +48,13 @@ sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11
|
|
54
48
|
sglang/srt/configs/deepseekvl2.py,sha256=sYMmoy5_LlDXht7MTi4QGYOaiE8iMGUO44bnuOu4i8I,23683
|
55
49
|
sglang/srt/configs/device_config.py,sha256=kdwFrk5myAURxdp4rSr8ANpBpSJfuBDoT-kuCyuscRs,442
|
56
50
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
57
|
-
sglang/srt/configs/internvl.py,sha256=
|
51
|
+
sglang/srt/configs/internvl.py,sha256=rIC-CBWJHy-Mjmk0_H3YcvVmZzeCRbXGo3dQMex-yeg,28141
|
58
52
|
sglang/srt/configs/janus_pro.py,sha256=yI2c_aWBIKiTcK6RZxK6hq8CIxyYRH_NN8uaSNKsrKI,19156
|
59
53
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
60
54
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
61
55
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
62
56
|
sglang/srt/configs/longcat_flash.py,sha256=Qp25xJVLq2K72Z80cXhcJxtqhagAdiPySDoevuT0Sno,3589
|
63
|
-
sglang/srt/configs/model_config.py,sha256=
|
57
|
+
sglang/srt/configs/model_config.py,sha256=0oEbC4bxtfPckBuY_p6uXHB1vDXxhkvJCpr9cPbExwI,31712
|
64
58
|
sglang/srt/configs/step3_vl.py,sha256=_Otgnym57DVgB_kZ__8c1_Ys5gSalA_K0ZuVjcG51T0,4845
|
65
59
|
sglang/srt/configs/update_config.py,sha256=GEf-XhL8JPrbX9-Hz8V7S3M6YTg76DVdIhc_4YdMDtc,6291
|
66
60
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
@@ -87,7 +81,7 @@ sglang/srt/disaggregation/decode.py,sha256=EELA3krHp4YtRIpUYU0-9LSFd7XQuvKn3yiHG
|
|
87
81
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=Iu7ehHGAfYIVATtClwX6y-6zxWs-JyDlMotYo_5yuUc,6598
|
88
82
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
89
83
|
sglang/srt/disaggregation/launch_lb.py,sha256=x355ULx1tUOkSSDae5INMQoG8sPC-l-hMh4FBk9MAaI,3439
|
90
|
-
sglang/srt/disaggregation/mini_lb.py,sha256=
|
84
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=fA3U-mje6d-K9Mlh3IOsJz29JGMzuro1xG68NWiefpY,15601
|
91
85
|
sglang/srt/disaggregation/prefill.py,sha256=gf8ju_REf5FxPg_QtmlMEipeo1N5muUcZHRkaKtfMhY,36286
|
92
86
|
sglang/srt/disaggregation/utils.py,sha256=evdv4AkQxJzTqdO0jrdAr7vHUbBSCEXMzNREh0FoRLc,12294
|
93
87
|
sglang/srt/disaggregation/ascend/__init__.py,sha256=-lxnica6fZYmYNpKwmE8yESUpQ5Sxf2DiZoBHzboKc8,146
|
@@ -108,7 +102,7 @@ sglang/srt/disaggregation/nixl/conn.py,sha256=eSof87fG21Dd4COszfnbeXIxne3TWvw0mS
|
|
108
102
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
109
103
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
110
104
|
sglang/srt/distributed/naive_distributed.py,sha256=5Kcfapzz61G3TtScTZrHoWa4bf6Vr27GlMcBAGMz7tQ,3260
|
111
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
105
|
+
sglang/srt/distributed/parallel_state.py,sha256=VhtVXFLhnvk8cV_eMQIMkOYwHkAU8bNzNwg2hHMJ4Gw,65943
|
112
106
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
113
107
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
114
108
|
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=Q1kkKPKFPV0QMmKLyjOBlOnX8-Pr4UeGBZYkG6j0gc0,16570
|
@@ -124,19 +118,19 @@ sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=IrSrnpZnii0E
|
|
124
118
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
125
119
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
126
120
|
sglang/srt/entrypoints/context.py,sha256=aD-94xkD0komuGO5gtYUoJKCHdc4hAipMxQt04yVRGA,8030
|
127
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
121
|
+
sglang/srt/entrypoints/engine.py,sha256=wNEYxQTVFHt9EvMzQr5zutX9Cb7RDDn64c8Xckuwhsg,33490
|
128
122
|
sglang/srt/entrypoints/harmony_utils.py,sha256=01T-A5GBUm2b306PcxNEg2rfx4cykBcqNYrzcXTWBlc,13590
|
129
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
123
|
+
sglang/srt/entrypoints/http_server.py,sha256=X76_ngkT70e_wSQoe7jKfO_tksrCJafXu86JBve50gs,49834
|
130
124
|
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
131
125
|
sglang/srt/entrypoints/tool.py,sha256=aAXEjBqkr5j6_IgRL8fZCKgoDPY2TikM20-LQXU9TaI,2709
|
132
126
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
133
|
-
sglang/srt/entrypoints/openai/protocol.py,sha256=
|
127
|
+
sglang/srt/entrypoints/openai/protocol.py,sha256=CLFG9mE1WL5G4xomK-frtYxXSNfq0lqoCLisYESvMlw,28737
|
134
128
|
sglang/srt/entrypoints/openai/serving_base.py,sha256=epD6J7K72p6TP8o2dGYf-a76nXeF80vFhPRpWts6684,5445
|
135
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
136
|
-
sglang/srt/entrypoints/openai/serving_completions.py,sha256=
|
137
|
-
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=
|
129
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=s2xUCcorZ8K0I5iWH96hpVyPtqMGhP291Cn1bRvSzYM,43141
|
130
|
+
sglang/srt/entrypoints/openai/serving_completions.py,sha256=llA6beGNvStaC9yBvrJf3kmFiMtvxxiwWIZHV55PqwU,17860
|
131
|
+
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=uqyp_dKtLDBQwVNpStUvMuk2knNU1uoaVLJ9mL26wtw,6281
|
138
132
|
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=8n6y5kC6UhRpWrDtzH0eIp0dznW12FT60MLCR4bvD2U,3333
|
139
|
-
sglang/srt/entrypoints/openai/serving_responses.py,sha256=
|
133
|
+
sglang/srt/entrypoints/openai/serving_responses.py,sha256=dR60Y3kWedLRjVFBTUObHt0GFiI9VnWdRDMqq8cq3w4,53405
|
140
134
|
sglang/srt/entrypoints/openai/serving_score.py,sha256=ebAts-m6Pq-LTgFKwggkywBUrAgUSppHHVEzgwYHUzo,1955
|
141
135
|
sglang/srt/entrypoints/openai/tool_server.py,sha256=rRNGELPV5RHONp55MYkO4_b0NPsPffJnWg-gMYwDSTc,5659
|
142
136
|
sglang/srt/entrypoints/openai/usage_processor.py,sha256=9LTB5rqdRuMKyZrIXiUBuF_WKaSg9X45YdzERDxbtCY,2746
|
@@ -159,7 +153,7 @@ sglang/srt/function_call/deepseekv3_detector.py,sha256=DhO3tUX1nvFlfRkHJ1Vm_7OMX
|
|
159
153
|
sglang/srt/function_call/ebnf_composer.py,sha256=f5Lqn3mtTtJ7LCJXAurVw2k4Zp5LgbWywQv7GsxSoPw,15000
|
160
154
|
sglang/srt/function_call/function_call_parser.py,sha256=55bbToi2wWGmahfyDX1YeFpndNCwTa23ZdNsawMidbc,8333
|
161
155
|
sglang/srt/function_call/glm4_moe_detector.py,sha256=FS4Jhyt8_2xTTytNsQhzlNds2VQO_JIp3tKyCf7PtF0,6939
|
162
|
-
sglang/srt/function_call/gpt_oss_detector.py,sha256=
|
156
|
+
sglang/srt/function_call/gpt_oss_detector.py,sha256=HLthoD4NHl3EKM04R5UL0CvQEYuwFtwtGH8DwHRTCoY,8306
|
163
157
|
sglang/srt/function_call/kimik2_detector.py,sha256=u6GXTAcvqWstkuDgxZMeKlpp9zu3V4OTZ8yaplLxEGM,10109
|
164
158
|
sglang/srt/function_call/llama32_detector.py,sha256=trZja7IXc2IWUko5PRj7p4pRU6XCVjtxr-7qJNr0EWo,3647
|
165
159
|
sglang/srt/function_call/mistral_detector.py,sha256=Ts2HrJdu5r2lCCMVKPZfnCds9pt1K5H1EaOQrF_HD60,4686
|
@@ -170,23 +164,25 @@ sglang/srt/function_call/step3_detector.py,sha256=SAibrispu0peDQzqOG2-V93KGHtV6U
|
|
170
164
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
171
165
|
sglang/srt/layers/activation.py,sha256=mAa6E8xTDs6RyuBO0kNXaIuWxOlKfu8jQH5YG9PblhY,8213
|
172
166
|
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
173
|
-
sglang/srt/layers/communicator.py,sha256=
|
167
|
+
sglang/srt/layers/communicator.py,sha256=NYP2IGKs5eK4X9DNG0MBbKShI1fmT2TExOOuCXR8Nlc,24111
|
174
168
|
sglang/srt/layers/dp_attention.py,sha256=35GQIpO8HpF9mtLQSJe2RW2a5rblTLvzAbr1CL0PbSg,15286
|
175
169
|
sglang/srt/layers/elementwise.py,sha256=PjYv7Sk-zKbG9WiGlYDKsxvNrnxT2N1Q8bA2BWvA1Uo,18771
|
176
170
|
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=hnVVS_VsWukTYhREubWs2KcJ1GjVMEI9ECqxqOMXZv8,6729
|
177
171
|
sglang/srt/layers/layernorm.py,sha256=hvfU36Q_SpHR7renSbXuI5WnENE_i5Z7TuU4dxRN7fw,10614
|
178
172
|
sglang/srt/layers/linear.py,sha256=evhlZ_aPFce-m89zYDeEfSrYAOoaMk5BC18vDjGPzjM,53508
|
179
173
|
sglang/srt/layers/logits_processor.py,sha256=jCLgKuU8r-T0ZdSjWEWNhtmx408f_NTKVCW20_dn2ZQ,26969
|
174
|
+
sglang/srt/layers/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
180
175
|
sglang/srt/layers/multimodal.py,sha256=vNswe0J0maeBiN8ehlmxfs-YYlrmMllYl6Nc_Y57Neg,5114
|
181
176
|
sglang/srt/layers/parameter.py,sha256=jCg0G-12GZqTa9gGOqEtVCsnnuBGnYg0VmF6pc6oCFg,17455
|
182
177
|
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
183
178
|
sglang/srt/layers/radix_attention.py,sha256=MpugwaqiY2zPTeg7FVW41OljljCXmYVvHZ2MvneF6PI,3745
|
184
|
-
sglang/srt/layers/
|
179
|
+
sglang/srt/layers/rocm_linear_utils.py,sha256=7PPh-5H2IYjiLp_g_szzVBsmiMacZ1RtjVtjdrdFJKI,1374
|
180
|
+
sglang/srt/layers/rotary_embedding.py,sha256=0SzOf8SnUbYNxeFLH5tIGuK_Hv0rRONRhRPGZLduxh8,73462
|
185
181
|
sglang/srt/layers/sampler.py,sha256=RIcvSriJaHpFhjNPX3CzJzn4Lwy9H3MTPBeZjqAZq9o,11762
|
186
182
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
187
183
|
sglang/srt/layers/utils.py,sha256=E7PHisGiD9ZmLS4RWqCUZWxAQJbfc0WaTfRZ37gUlPI,1077
|
188
184
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=x0421kNUgnAb5LnkJR6O67vGZ0ikSD-ThluV3QGsZ_8,22673
|
189
|
-
sglang/srt/layers/attention/aiter_backend.py,sha256=
|
185
|
+
sglang/srt/layers/attention/aiter_backend.py,sha256=WUOf8qba_wD7OgoJMKIsXR6_VdZD18alB3FajafBGSc,43887
|
190
186
|
sglang/srt/layers/attention/ascend_backend.py,sha256=zmEz1NfytWADYFmCGBVIGXhVAT5GX_z5fnC8-1r5pK4,23334
|
191
187
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=_vM05ddWy6SaoqWYPR8w5lflSE4MhcVFR271Q9EKK8E,3600
|
192
188
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=PB5BjbJHhmTg_t0kXfarTI6C3pPvKhBAqvCSGGajou0,9846
|
@@ -220,18 +216,21 @@ sglang/srt/layers/attention/wave_ops/prefill_attention.py,sha256=viTUit0rxjVV5Ua
|
|
220
216
|
sglang/srt/layers/moe/__init__.py,sha256=63TxUpSiUpVg1SDY1zdlTg3WFJzAc7WSndOViOmUv4E,835
|
221
217
|
sglang/srt/layers/moe/cutlass_moe.py,sha256=JKJED-4709ndP5AwhQ7Vi04GJjw5d9Xl_mWOsZPZ3U4,14298
|
222
218
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
223
|
-
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=
|
219
|
+
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=pUvYkbm3kD5IBjVuJeehU_hvEvdNcYcO2eRZXDc6iLI,7005
|
224
220
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=8SAToE4B-22H5JsENZgJ1Io6QfE5-D9ItWLtbGksFQQ,3372
|
225
221
|
sglang/srt/layers/moe/rocm_moe_utils.py,sha256=07Z99bTV3B-b2Cbm-odhGpx2twxtnVpYvaDMBE1K3LM,4555
|
226
222
|
sglang/srt/layers/moe/router.py,sha256=eUNu_Uz5VB2FOZzZyYuZo5pokCVBS17_fcjHQbmvDSE,12181
|
227
223
|
sglang/srt/layers/moe/topk.py,sha256=r8pE6eJ8dprfZxaw8VcfrRvSp6_xDNPkr0tajmG_CZc,31349
|
228
|
-
sglang/srt/layers/moe/utils.py,sha256=
|
224
|
+
sglang/srt/layers/moe/utils.py,sha256=b5FFsyKUgyGmNhoyVtB37h0JdNnjL6BH0RuKcjXeJzE,5925
|
229
225
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
230
226
|
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=Acg6dW-zVDQ95vuBVuzxb5SUFFxhLCewk_tVSZeuma8,46158
|
231
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
232
|
-
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=
|
233
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
234
|
-
sglang/srt/layers/moe/fused_moe_triton/
|
227
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=uAHuiAILb3XQi9t1JGMElfzvsG9cKIDMXs6ezEGhGvY,27776
|
228
|
+
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=tis0ZJmih7gKHCurbLtY_o-bY3K4MOzQLYLC3ftIOf0,977
|
229
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=q_L-eZh9pBP3KZLipv9cRe2WpezNrHMz8NzMy97TV0Q,23178
|
230
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py,sha256=fFnRcXA6r0gnD_7EQmb8NacQJRJ8YHsmMZw2khlClTQ,7687
|
231
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py,sha256=z10ZJLrFFhgB5_cEFrvMt6bnwe46T5Vzz4nvMl4ErGU,27776
|
232
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=TI3p8FOJJjpoyE7VMngs9BPeiiN9M9XHZJRWVTWtiH0,39637
|
233
|
+
sglang/srt/layers/moe/fused_moe_triton/moe_align_block_size.py,sha256=U93mxPPU2RP7d3QRSvoG3OCtUQIK8YhQfHf1ZGeREmY,3284
|
235
234
|
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk0nPWQelgvi1rV9Z72FetRo6p7E3rsYs,10986
|
236
235
|
"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
|
237
236
|
"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
|
@@ -423,6 +422,7 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
423
422
|
"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
|
424
423
|
"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
|
425
424
|
"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
|
425
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=RbJYTRfjP_3-ytfj53W_w2jFpZ9xwMaqoKW52pkgP3c,3257
|
426
426
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=64,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=QEk8bE-GieZltTiv3ig__ScM9Q_4K-c75UzIuDrGmPA,3232
|
427
427
|
"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
|
428
428
|
sglang/srt/layers/moe/moe_runner/__init__.py,sha256=piJQmSz7BOBaxVd0gGMgRLzaD21r7PH1NEDOK5hktYk,97
|
@@ -446,16 +446,17 @@ sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V
|
|
446
446
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
447
447
|
sglang/srt/layers/quantization/marlin_utils.py,sha256=aM3GU7b7rHNZE-tZjRSrtOaPWzSaMcLxck4he8MlEVI,26344
|
448
448
|
sglang/srt/layers/quantization/marlin_utils_fp8.py,sha256=iSjq-ikPOTU5plrWNTW4MletKLySIrNl5NhQmY6FyAo,12508
|
449
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
449
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=lA7LkNiSRtGHbSUV2bngnrHyeAOB4hRP317sOkh5vaE,54245
|
450
450
|
sglang/srt/layers/quantization/moe_wna16.py,sha256=brU0nG6StgjGuuhOjpeoh-wJVZ1SUgbuHhiDR1hibbw,18905
|
451
|
-
sglang/srt/layers/quantization/mxfp4.py,sha256
|
451
|
+
sglang/srt/layers/quantization/mxfp4.py,sha256=J7nnMvL1BslHmfiDb-pRFScAMy0coWU8xeuxvfaHmEQ,31537
|
452
452
|
sglang/srt/layers/quantization/mxfp4_tensor.py,sha256=bGeCXlIOhmFZFGWp_lITkIRDEgGUaLpawDvMy1cTOmA,5389
|
453
453
|
sglang/srt/layers/quantization/petit.py,sha256=74Jn0eICq23v_b4rEctDaYTINtbqkdM6IXycT-_FbbI,8954
|
454
454
|
sglang/srt/layers/quantization/petit_utils.py,sha256=-gy4zMhqNoIA1R0n7-5C0efV54jHonCUgPDUUFjGsyM,3245
|
455
455
|
sglang/srt/layers/quantization/qoq.py,sha256=jM96uJfKz3vo1B6SSIrQXNT3vnD3UJrepK2eY-tSQU4,8139
|
456
|
+
sglang/srt/layers/quantization/rocm_mxfp4_utils.py,sha256=Z4pYWl6ExOXq2qfTHorW16hVbJ-Rk4G8Wrxn_x8boHE,327
|
456
457
|
sglang/srt/layers/quantization/unquant.py,sha256=CxsOEYqYIfanKHo0ooFArbVz2ueX3vBWnYHE8gtnzdQ,12996
|
457
458
|
sglang/srt/layers/quantization/utils.py,sha256=d4eaS4-Z4q3GRgb4HDMr2EoWEdQCefrVdJufK6n_NQY,18509
|
458
|
-
sglang/srt/layers/quantization/w4afp8.py,sha256=
|
459
|
+
sglang/srt/layers/quantization/w4afp8.py,sha256=Cm_KjJQu-XKqSKh6usJ5tNXARm6F5n_C2P1c1NuYdC0,11720
|
459
460
|
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=wzJi5jeTnbf-01iehOVTTCu_262rlMh9AQ2rogKWBmo,9981
|
460
461
|
sglang/srt/layers/quantization/w8a8_int8.py,sha256=cOKbhWxFlv6hw5dSs8ExPBXFcTwudwR26m3CAoOhCSs,35342
|
461
462
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
@@ -619,16 +620,16 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
619
620
|
"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
|
620
621
|
"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
|
621
622
|
sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
622
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=
|
623
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=PI9r3PHCMK9EgpoFuBgR4jvokA5sBz8zyC47ps3wet4,8164
|
623
624
|
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=8C4xyO58N3Zl8h-fYddUpXDs3mnSqjYbaLt12cPB2XA,778
|
624
625
|
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=vCj5vdAshEB9mAgSUYXhgJ0bd1Ithmu_n4-m_IWUbd4,2531
|
625
626
|
sglang/srt/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
626
627
|
sglang/srt/layers/quantization/quark/quark.py,sha256=EqQvWzAc6nd_yl6UIMIwmozKif4I8fRNfBum040UUEQ,14613
|
627
628
|
sglang/srt/layers/quantization/quark/quark_moe.py,sha256=yLRmytEwBMZd7ShzHVX6-w_8koyiRrvIxKx8g02qRZw,6789
|
628
|
-
sglang/srt/layers/quantization/quark/utils.py,sha256=
|
629
|
+
sglang/srt/layers/quantization/quark/utils.py,sha256=zZHRe9mjxGp16_OJ5Qy_UtnQgipl3ZRZUmruYvyEm_w,7445
|
629
630
|
sglang/srt/layers/quantization/quark/schemes/__init__.py,sha256=z1LHBPqkxAS6Wp70DWwESOSixWpIhIQwz1IHcWDdURQ,167
|
630
631
|
sglang/srt/layers/quantization/quark/schemes/quark_scheme.py,sha256=b8-Djo-UQAwgxSWViKDoEP5dOSesnEBPyozX-osB3WY,1478
|
631
|
-
sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=
|
632
|
+
sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=sW57dU7HoxQGVbzUhyhRirGWA8oVpENB4NTzO7URGgU,4198
|
632
633
|
sglang/srt/lora/layers.py,sha256=3RwD5TC4zO8A2Haz7ScIT5vc_neU9RHM3DoamKttVkw,10838
|
633
634
|
sglang/srt/lora/lora.py,sha256=lPPEJavrfANXDzdmKEg4hbgmKIiEr3NU7KNJeaaKTB8,7393
|
634
635
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
@@ -643,39 +644,39 @@ sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=QURCYxHNR8Ls4SQtt3dvdgjvdDVh
|
|
643
644
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=z9BB84Xu_MjwCu5v9Yvji-FkIzfEjDySAFybc4WYv7A,6483
|
644
645
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=Ksova04wgeGsFqGOXWqJtMYaHgyUYcx8VU42BZQOkVA,5129
|
645
646
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=VqCAFvUtq_l-0RGIkx3W_fzD55QcW2FAcqpvSHOBFp4,5115
|
646
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
647
|
+
sglang/srt/managers/cache_controller.py,sha256=ttQsnjInZhZ05Eo2acc8MWJFemqjsaKmhIy3wwIJVDM,33668
|
647
648
|
sglang/srt/managers/configure_logging.py,sha256=8sNXZ2z9pBWOwn-X3wyz013Ob8Nbm1zDxRkxoZjH-l4,1633
|
648
649
|
sglang/srt/managers/data_parallel_controller.py,sha256=VvEkidmYCGAFTv6upEHf_tyTvkM8xLhCyOnLJGWL6BQ,14592
|
649
|
-
sglang/srt/managers/detokenizer_manager.py,sha256=
|
650
|
+
sglang/srt/managers/detokenizer_manager.py,sha256=mVEzkaCTu0MUe8QuwQC9uReOJgTWVQYXcItlDS2gYK4,11594
|
650
651
|
sglang/srt/managers/io_struct.py,sha256=ebAKRqBYj4slW25-dWs51JAW6caPcvuIMlSoJJZd8wo,40503
|
651
652
|
sglang/srt/managers/mm_utils.py,sha256=J5hahCJ7HAKhJtGzV6PRa5HB9B2NjYwWGYMqIgiGC60,29444
|
652
|
-
sglang/srt/managers/multi_tokenizer_mixin.py,sha256=
|
653
|
+
sglang/srt/managers/multi_tokenizer_mixin.py,sha256=4MPzKk6Q8iFSPu9owuF7euOJxfDspm0N1Oi-KOh63FM,24844
|
653
654
|
sglang/srt/managers/multimodal_processor.py,sha256=cnWpu2G79v1a6FJB_FriLxESgGUbfC3GptLmeRVVgew,1801
|
654
655
|
sglang/srt/managers/schedule_batch.py,sha256=9lhBnf-siQjsThD8FRyhiF50N-LOE7dfoPr1uzklnjQ,77170
|
655
|
-
sglang/srt/managers/schedule_policy.py,sha256=
|
656
|
-
sglang/srt/managers/scheduler.py,sha256=
|
656
|
+
sglang/srt/managers/schedule_policy.py,sha256=COLswvMEcLyufAfUdO8HKk6PJAmEBnjbrzk2Ip2-KMk,22440
|
657
|
+
sglang/srt/managers/scheduler.py,sha256=XHoWJrBO_05piCesGiIy6O8k3ZwqFi0kKxN3wowVKxE,107087
|
657
658
|
sglang/srt/managers/scheduler_input_blocker.py,sha256=zP8xU_UmU2H0AB6sEqvivDcDB1QDgTauNDYDIJ7Nez4,3683
|
658
|
-
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=
|
659
|
+
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=SMlBNWggXTwVJdedocw-F7J6eczaNGr0VayBnSVDptc,14567
|
659
660
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=CLwF58GTV7PkyYUoC-R7ROA-cZt8di9_9n2pajacxUY,31511
|
660
661
|
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=A67lC_U7HUCf_znatXK51orC8xeFNGouJ866HH_Y-yc,11402
|
661
662
|
sglang/srt/managers/scheduler_recv_skipper.py,sha256=8rVQCBjn9f26Th4XbeUS3fEsvo1GI029Me28wMjcKRY,1103
|
662
663
|
sglang/srt/managers/scheduler_update_weights_mixin.py,sha256=uk7Dusr8EJBDRdcuQNIoedj0oP4tmSWrUbEqmjclwnk,5813
|
663
664
|
sglang/srt/managers/session_controller.py,sha256=FGADRGSkRmS76o_BQ2fivpgw0Q5Q-K0Ws3aezH41YSc,6041
|
664
|
-
sglang/srt/managers/template_manager.py,sha256=
|
665
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
665
|
+
sglang/srt/managers/template_manager.py,sha256=M4EshVv1OhKxUAGQPP4OntRkSkUVvG93457xsYfWnQk,11968
|
666
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=YtD3nCYLQTgpsdlywfxzql2SeJNhuFBRFZMFxvcsqlM,88307
|
666
667
|
sglang/srt/managers/tp_worker.py,sha256=n_DqSD4JqOJYjdZrchOpmpuTazRw-AUrs6RPQYuAPyQ,11933
|
667
668
|
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=NXjrBT7lvdUlDDNFzEQyFYCerpqj92sNl2YynGhQj-Y,11118
|
668
669
|
sglang/srt/managers/utils.py,sha256=WbUdADEdiSOoQNfwjfU64mNaXoskEveBO1HP_t0FJtQ,5687
|
669
|
-
sglang/srt/mem_cache/allocator.py,sha256=
|
670
|
+
sglang/srt/mem_cache/allocator.py,sha256=47M3lrAv9k2MJXQc82oGXokLb_3u1A8LFNL9WmgIBN8,18219
|
670
671
|
sglang/srt/mem_cache/allocator_ascend.py,sha256=i0KPCcFlzGkCIjW8ph3IPkBXAWTqq4-AeaoG1wR--lw,4471
|
671
672
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=hLS2ncTMAz7Kpdk5pNwn5c6g8b61_K9OCBL4Vj1xsYc,2801
|
672
673
|
sglang/srt/mem_cache/chunk_cache.py,sha256=jbJeEEZ5_WYEF_AnDZIAu2sMD4hAGAd_24F980fjVwU,3199
|
673
674
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
674
|
-
sglang/srt/mem_cache/hicache_storage.py,sha256=
|
675
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
675
|
+
sglang/srt/mem_cache/hicache_storage.py,sha256=AoFci5-hvaBF6TfXtyoE9aJpDk794guiruS76h_Y6dI,7548
|
676
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=qjJkR0yLMyUMbAHsurlkER1tnaPY39DejL5b0ymRX54,29206
|
676
677
|
sglang/srt/mem_cache/lora_radix_cache.py,sha256=4NbK0Rc15kTiCOSsthyM6WsZarMK2MNhtsNqYMakJ5k,14369
|
677
678
|
sglang/srt/mem_cache/memory_pool.py,sha256=EGZtQsgXDOuySeEBdV6jBIt9ZDvqMsErNPe6P5ifHh8,39540
|
678
|
-
sglang/srt/mem_cache/memory_pool_host.py,sha256=
|
679
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=NXEVa1XjA8sXwpklvvWYjb0k6-gUgdj1P4MHBO9ybfA,26425
|
679
680
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=zPnQLQhBZ6zsUpCQPSoNkrB9EEvpoDQS4mU7c3sRWjE,2171
|
680
681
|
sglang/srt/mem_cache/radix_cache.py,sha256=U0KEjQNcwhdFWnXYTMhDkxpiazAD1ttbADEkGPHiiTU,19116
|
681
682
|
sglang/srt/mem_cache/radix_cache_cpp.py,sha256=YuYt4xNzfmNNSkwaAk3VLWcZI74_XQobIyEgt96f7Qs,9284
|
@@ -683,19 +684,20 @@ sglang/srt/mem_cache/swa_radix_cache.py,sha256=hV5OOmAqu4UT80BVsu7lhGewcbq-u__JK
|
|
683
684
|
sglang/srt/mem_cache/cpp_radix_tree/radix_tree.py,sha256=tQZpz-H6HxNAQe9mYqt6aX8mfDZyu_fbJTcCNK-Ns1M,7179
|
684
685
|
sglang/srt/mem_cache/storage/hf3fs/client_hf3fs.py,sha256=WV5M9UPPLUMMjU3Mpp6HBqyCQpGBuMyj-N5PwQcNo5k,5178
|
685
686
|
sglang/srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp,sha256=dDYPtxmL6OFhEyv_GuTgzkTDpBjcD0EK8kphnn7eaGc,1133
|
686
|
-
sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py,sha256=
|
687
|
-
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=
|
687
|
+
sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py,sha256=lJ9Jp2kOgQQaUihxlO9l-W8fYfOMa1h1y0WAtzzFGLM,17850
|
688
|
+
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=g93ysuhBfO3d9ARopBNat7znrn2cxW-PVbDEYpjlFJ8,15241
|
688
689
|
sglang/srt/mem_cache/storage/hf3fs/test_hf3fs_utils.py,sha256=g2h0Woa2CK39pRTigHCVR_hq095dTaC70lCIAIs9THM,1089
|
689
|
-
sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py,sha256=
|
690
|
-
sglang/srt/mem_cache/storage/mooncake_store/
|
690
|
+
sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py,sha256=6uQ79XFbHBpyO-cPhT8E3mY6VYNkk9WqZQntSledwAQ,10588
|
691
|
+
sglang/srt/mem_cache/storage/mooncake_store/test_mooncake_store.py,sha256=6TiqbzEIL71DC7wL1B-Q-SMMZRYsz08sg-dZYeMzmAc,4930
|
691
692
|
sglang/srt/mem_cache/storage/nixl/hicache_nixl.py,sha256=bau9Jsp50lpEiy_osgb-dYzeoUkPWM03x7Q8z2BpKaU,9920
|
692
693
|
sglang/srt/mem_cache/storage/nixl/nixl_utils.py,sha256=KXkwMrbWwIOUOASINnUo4HyheiMd-93smmwGLv0CacU,7463
|
693
694
|
sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py,sha256=vENVvGAd3PqcQEFA812wPoSBYhRemLr8Sfh1LQa0INU,9609
|
694
|
-
sglang/srt/metrics/collector.py,sha256=
|
695
|
+
sglang/srt/metrics/collector.py,sha256=QD-2KyW_3MSj82e-uzKvP0sFBax-0yA8JV5NmT0D-Bw,20667
|
695
696
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
697
|
+
sglang/srt/metrics/utils.py,sha256=BkLQFOfzNknDJ5zc4wOqkJ9awLuQE7EtwA0EYjlJg7I,1715
|
696
698
|
sglang/srt/model_executor/cuda_graph_runner.py,sha256=fZT_CQwhfu7kdnliKu5lYM2tunU0u3wBoIlCxm4FXCA,33920
|
697
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
698
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
699
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=51MUq8eR2nuOToPC85kCIQ_blhDJSLm_EuZGJiJgCog,40553
|
700
|
+
sglang/srt/model_executor/model_runner.py,sha256=11iLjACbaN_Huf42NWqLZ4RpXhn1jhs4Pc5WAjrTXvM,78481
|
699
701
|
sglang/srt/model_executor/npu_graph_runner.py,sha256=isp2Plkf4b_gdjptYxJhTJk7JL21Jg-Md3hAYIuSVxM,3424
|
700
702
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
701
703
|
sglang/srt/model_loader/loader.py,sha256=RGcqzjQnOK2W-M3IURnmocNm8vZRG3ly_-76nye79Tg,60189
|
@@ -712,7 +714,7 @@ sglang/srt/models/dbrx.py,sha256=117gwrB_o8VlACwDH5YlXkPfuS7t2Mh-nyJvpNpIYxs,159
|
|
712
714
|
sglang/srt/models/deepseek.py,sha256=M7nyHcAbTIs8vc1g6u00oy22-pp704Xp4T3clBzu4xM,17460
|
713
715
|
sglang/srt/models/deepseek_janus_pro.py,sha256=td8xGs6ARfJ8AQCYwUhMOZoWigrAs7m3trF5-kXCqik,70418
|
714
716
|
sglang/srt/models/deepseek_nextn.py,sha256=uoiJxAVl9DX7bQcjyuouAZz6W-cB1HMubcirTBghyR4,6115
|
715
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
717
|
+
sglang/srt/models/deepseek_v2.py,sha256=1b4OIKt5wCTfCYUOI_XUjMHVELktA5jJrYNjxDYo77Q,115498
|
716
718
|
sglang/srt/models/deepseek_vl2.py,sha256=7X3gI4DE7guUtNJvMLf06jO8MUHKa2Aan8evZg5hsXc,13061
|
717
719
|
sglang/srt/models/ernie4.py,sha256=7dP7_d0i86tv8Mp21Ew9RdsFr6TskIkm8UtUd8zFo00,16067
|
718
720
|
sglang/srt/models/ernie4_eagle.py,sha256=E7f-ygCcY8pIoyTMKFyVC2uRcG59-_RaQTO4gd5_uWI,7223
|
@@ -726,13 +728,13 @@ sglang/srt/models/gemma3n_audio.py,sha256=isgKfjA5UieYawxU6medL2ssXlzYPqAbagDBnL
|
|
726
728
|
sglang/srt/models/gemma3n_causal.py,sha256=kBDlpSWAg6ZDmUPe08Q7sj5CbdVD_0h07zwJw8sKu7I,36335
|
727
729
|
sglang/srt/models/gemma3n_mm.py,sha256=XTY3HIUt4xv407aS_2rXdfxD3G1sp4z2kVhdC4vnxIQ,20354
|
728
730
|
sglang/srt/models/glm4.py,sha256=dijzVTTgg8zyJ3gga95MKY0WwqwnuAaf-VIV93OFAmc,11433
|
729
|
-
sglang/srt/models/glm4_moe.py,sha256=
|
731
|
+
sglang/srt/models/glm4_moe.py,sha256=X57Pw4O7025eylkSnaSEw3ELfnmlGDt0DCyhD977Bcg,41994
|
730
732
|
sglang/srt/models/glm4_moe_nextn.py,sha256=EuDWOBSd0oFfdvloePlpzAL81M_L7oz0BiWm74RQioc,5943
|
731
733
|
sglang/srt/models/glm4v.py,sha256=WtDvH4691H6IKrcGBrkBpweSm_iFK61bMEfvqpbblmc,23790
|
732
734
|
sglang/srt/models/glm4v_moe.py,sha256=qgJtWyRI0dy9qcTMXHxhBZp-ghfghV3PLhpOXgSAW60,17313
|
733
735
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
734
736
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
735
|
-
sglang/srt/models/gpt_oss.py,sha256=
|
737
|
+
sglang/srt/models/gpt_oss.py,sha256=6g7PE6EiOLDipmhV-XKmBcuoCGbhH6SU6NwsSoB_FJM,44469
|
736
738
|
sglang/srt/models/granite.py,sha256=8q92shxVPAp_cJDohJATffSGd7Z0Oi-vF5jpY6DlK4s,19840
|
737
739
|
sglang/srt/models/granitemoe.py,sha256=j1rgZ62CbBioECjUblDCw_NneDQgY_QJODsI0fqXVO8,13779
|
738
740
|
sglang/srt/models/grok.py,sha256=8KCR13LtdnhswJrIwgb0sdFW0OxCA8GQ0fbN8gb856E,40518
|
@@ -741,7 +743,7 @@ sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo
|
|
741
743
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
742
744
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
743
745
|
sglang/srt/models/interns1.py,sha256=E4SyJWocXZ5rAuAV8kj569OHo57r04W4hmq1CF6oiFs,12516
|
744
|
-
sglang/srt/models/internvl.py,sha256=
|
746
|
+
sglang/srt/models/internvl.py,sha256=iQm2wDtkcyjPYoV9oY_jQ3_7WvhP315eP_vZEiQX3uw,27062
|
745
747
|
sglang/srt/models/kimi_vl.py,sha256=XulRiufQzOSWZe8-bUl2OEdznvsVU9OBsEYipaX3YkM,12877
|
746
748
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
747
749
|
sglang/srt/models/llama.py,sha256=tdyUon6icwzqo4XTAkFxVA2f82g80AGr9ZezK1uXmkM,28126
|
@@ -753,14 +755,14 @@ sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OW
|
|
753
755
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
754
756
|
sglang/srt/models/llava.py,sha256=xzYip_BAwpzSIdZre43LZiyTpFISa0ZCLdO6LUSbaCg,37702
|
755
757
|
sglang/srt/models/llavavid.py,sha256=-CSk0RJ2MQeb81sh-RISeVJFaI-XWY6nR6_I594MkME,12818
|
756
|
-
sglang/srt/models/longcat_flash.py,sha256=
|
757
|
-
sglang/srt/models/longcat_flash_nextn.py,sha256=
|
758
|
+
sglang/srt/models/longcat_flash.py,sha256=gyElibQ9q_qq4tBA7eah0f3bLSzvMEpgD_n6CcRyG9M,41055
|
759
|
+
sglang/srt/models/longcat_flash_nextn.py,sha256=oVy776-AE5z43C472oqHlcl9NfzDDEaQgGB1msZNdgc,29644
|
758
760
|
sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
759
761
|
sglang/srt/models/mimo_mtp.py,sha256=jSmqJAXu7G3OO7jW1oa2suI4H_Yl7u5ZT7w4lHFbHhg,7292
|
760
762
|
sglang/srt/models/minicpm.py,sha256=CzBJyZtfMpp8jvlEl29DHI7HLVq-CxuqP1UHwxIbaUI,14567
|
761
763
|
sglang/srt/models/minicpm3.py,sha256=Cflu4Tb2hxpjapRBZ5n4kX8a1nnFwffK-M8uHPRUra4,19276
|
762
764
|
sglang/srt/models/minicpmo.py,sha256=st8I13Ere5RkRHHQQN1LgZh1ybUA3_buxaaE4XlV8ag,76123
|
763
|
-
sglang/srt/models/minicpmv.py,sha256=
|
765
|
+
sglang/srt/models/minicpmv.py,sha256=_CnCR2y3RaYxhONAKFpBIuPQBrqn9Od4o7QnJw8CLR4,35884
|
764
766
|
sglang/srt/models/mistral.py,sha256=ni7PppA_5X4ivTnIps3yoEaMEL-G6Gaf9b5hGC1vU5Q,3475
|
765
767
|
sglang/srt/models/mixtral.py,sha256=ohZVFJ75QWuE2kBKD7Sd4fcx9YbbjA7JxnYAsOIfORU,17166
|
766
768
|
sglang/srt/models/mixtral_quant.py,sha256=UUIq7lpUonD9IoGePyl59oJYEcVwT9wUXvtVp5tjQ9Y,15406
|
@@ -784,18 +786,18 @@ sglang/srt/models/qwen2_5_vl.py,sha256=NBoGulAvr2dKk6sfTJQ3NAOIFtBvncbLi_nsUOhnG
|
|
784
786
|
sglang/srt/models/qwen2_audio.py,sha256=SOOsspU7J6eM-iSkms5op0nWhoxJd6QxmwXU2aQBEEQ,7776
|
785
787
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
786
788
|
sglang/srt/models/qwen2_eagle.py,sha256=6spFg6JYQGeUXLv2Q5eMkVzZvnqGyvW6SdVBtFMxlTM,4806
|
787
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
789
|
+
sglang/srt/models/qwen2_moe.py,sha256=m7E7Woq7BE3JR9f--ZHC3Aumrt06wNFq_Q8BCwqHJKg,26852
|
788
790
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
789
791
|
sglang/srt/models/qwen2_vl.py,sha256=ZRAL32Ymt4ZCBqB0JorXAm4ZBrECZ9EbaXKaTSikkQM,21366
|
790
|
-
sglang/srt/models/qwen3.py,sha256=
|
792
|
+
sglang/srt/models/qwen3.py,sha256=cfp7rL20_E4PyPii85gnXsfsje9b_WK3br-sbYikd0E,19324
|
791
793
|
sglang/srt/models/qwen3_classification.py,sha256=bdjAylXJCjXKjAho74nmtIMpEG0Af98N-aZQ-pKKMY0,3262
|
792
|
-
sglang/srt/models/qwen3_moe.py,sha256
|
794
|
+
sglang/srt/models/qwen3_moe.py,sha256=-Op20J68bwe6-fKsBlif1h2nlASqLHaTxWAxe_xiEuI,33198
|
793
795
|
sglang/srt/models/registry.py,sha256=kKQ5ruD6_c3JxWsykOoxt-hroSlslv-Niz0nYvHrhGg,3779
|
794
796
|
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
795
797
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
796
798
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
797
799
|
sglang/srt/models/step3_vl.py,sha256=joJmGukbGThLvwwbwrI4mCEVONH_U1dzFLWdpeJFoKo,35654
|
798
|
-
sglang/srt/models/torch_native_llama.py,sha256=
|
800
|
+
sglang/srt/models/torch_native_llama.py,sha256=qavMy0wjaX18pM7UJscjoOpSKWgDT_INlnImU6OJ4Lw,18327
|
799
801
|
sglang/srt/models/transformers.py,sha256=laA2h39MPeiAWKv4DEg0ydre-1pyXWFSRga-nwy1HUk,10244
|
800
802
|
sglang/srt/models/vila.py,sha256=3NiRHWOqXnCRjXmswAldsNtiE5zRILbScEsbhUzLZF4,9846
|
801
803
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
@@ -821,6 +823,11 @@ sglang/srt/multimodal/processors/qwen_audio.py,sha256=xkIFrHepF8Ok6MB-1OwVz1BmzP
|
|
821
823
|
sglang/srt/multimodal/processors/qwen_vl.py,sha256=tZOpz8dabyNvjS4hn0UxLf-EaEZH8kmHjyZaYRm9EZ8,10498
|
822
824
|
sglang/srt/multimodal/processors/step3_vl.py,sha256=9OI6UW9ybGbAnYN_S-5jh7TN8BGM_bQkvh1AHBJKzAQ,18350
|
823
825
|
sglang/srt/multimodal/processors/vila.py,sha256=vWgV1lTdjiFiTR8w-7fC66-L_tpOOD59c-c9NljGelE,2192
|
826
|
+
sglang/srt/parser/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
827
|
+
sglang/srt/parser/conversation.py,sha256=cmVT4SCqRYxprYvmftUC_z_TkhXCqYC9B2rVZsmQe30,38869
|
828
|
+
sglang/srt/parser/harmony_parser.py,sha256=YweG4azWm5jmzYGaAHEXSaORpgWctPpSGQk_jp5H-CE,23227
|
829
|
+
sglang/srt/parser/jinja_template_utils.py,sha256=XCuqi6iHQrtziUvhy22ePdh8WcS42O9sKxuXpM_bMXc,7836
|
830
|
+
sglang/srt/parser/reasoning_parser.py,sha256=3P5viZ4oCsz695rZULWnRKSYBJxouHjihdpZMBuY9yc,11159
|
824
831
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
825
832
|
sglang/srt/sampling/sampling_batch_info.py,sha256=ntC5ZHNth4uBVel4ZLdDVNC5xf8YS7pPw8k7Banb8rk,14792
|
826
833
|
sglang/srt/sampling/sampling_params.py,sha256=HbVcCeSXgPW19MRB-v0FTG1D-zHDAY6-toxyndSl-zI,6462
|
@@ -833,14 +840,14 @@ sglang/srt/speculative/build_eagle_tree.py,sha256=O9LJNaBflgJdWT94D-rGH1gJFJ18ns
|
|
833
840
|
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=jOIQDXsZ_CbxiTXnJjKtzYfOpc7-67dWwCaNcrv1Ebc,13938
|
834
841
|
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=QuPI0S85KirTlJArLpJXpywv7XQLborDGLFYwLUBnwk,15459
|
835
842
|
sglang/srt/speculative/eagle_utils.py,sha256=H-2aqm3REztUXLnmhi31ck3TWPPMVKc2CUkWBPsFK44,47785
|
836
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
843
|
+
sglang/srt/speculative/eagle_worker.py,sha256=HwGUBipr-Mj79TW_eDUeiW-yJ37kE4pTntN88bFbwCs,43689
|
837
844
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
838
845
|
sglang/srt/tokenizer/tiktoken_tokenizer.py,sha256=KJwr6Xlc7AdHegMTnAVKJlPpW59Z7AE27GTzFL78GwI,6222
|
839
846
|
sglang/srt/weight_sync/tensor_bucket.py,sha256=vp_LRrhULNnxiw9Tf56FcEckgUg07lifgv1lasG6y7o,3695
|
840
847
|
sglang/srt/weight_sync/utils.py,sha256=43zl3u8Svzj49p7Sk78xp7SWW83mlr3EH-OZFGUGy5w,4157
|
841
848
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
842
849
|
sglang/test/doc_patch.py,sha256=P9PYjBIVlZHvP9M34qS-8m1scmDP27ciNJNvZOdrUKE,1614
|
843
|
-
sglang/test/few_shot_gsm8k.py,sha256=
|
850
|
+
sglang/test/few_shot_gsm8k.py,sha256=zalplyHOYCnIwAnSQg-xlZl-Q-wGuMfjLdl9EJnUN7U,4333
|
844
851
|
sglang/test/few_shot_gsm8k_engine.py,sha256=h88s3HzEStA1zjQkR-AgIEOQMwJMSnPHkX_wGBWXUYw,3907
|
845
852
|
sglang/test/run_eval.py,sha256=VnbcmUhceDUU3-nXlZ6uQMM3MEvnZh1gzP3LXxYkuxc,4251
|
846
853
|
sglang/test/runners.py,sha256=uwLTGqSquJi5Js-FfkDB9ofsgNQYblV_n7wz7sPL3ww,33908
|
@@ -857,7 +864,7 @@ sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7
|
|
857
864
|
sglang/test/test_block_fp8_ep.py,sha256=n4X6ZKwuUUbV5Ofjg64ptlaFGI1LbRXDfFiJW1ELHgY,10546
|
858
865
|
sglang/test/test_custom_ops.py,sha256=PenQ8zM1wj5xwiVEPVzD37pO-x90aOfFMpCRZenaKsY,5709
|
859
866
|
sglang/test/test_cutlass_moe.py,sha256=ax-IYPm5tZjkZft0q8swHnzerOI4LB4JOLFaKGJVE-k,9629
|
860
|
-
sglang/test/test_cutlass_w4a8_moe.py,sha256=
|
867
|
+
sglang/test/test_cutlass_w4a8_moe.py,sha256=Ku9VCXEMJ3BwXtvb1A3FzY-zek-S-A4thWyX6m-1v-A,9219
|
861
868
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
862
869
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
863
870
|
sglang/test/test_fp4_moe.py,sha256=rJLkKW3glBMvI5Ed0LltOHi8zCReMa-WB50p5zGm6J4,10189
|
@@ -871,8 +878,8 @@ sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqn
|
|
871
878
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
872
879
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
873
880
|
sglang/test/attention/test_trtllm_mla_backend.py,sha256=quZ6SYuEH7J1YMcF8YO1_bwSNMz1gecpWRGauYjbUeA,42055
|
874
|
-
sglang-0.5.
|
875
|
-
sglang-0.5.
|
876
|
-
sglang-0.5.
|
877
|
-
sglang-0.5.
|
878
|
-
sglang-0.5.
|
881
|
+
sglang-0.5.2rc2.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
882
|
+
sglang-0.5.2rc2.dist-info/METADATA,sha256=2-vHFYEYNR5ac7zg3Ya1YLE8M54OqzUivXEr1r6E_JA,28151
|
883
|
+
sglang-0.5.2rc2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
884
|
+
sglang-0.5.2rc2.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
885
|
+
sglang-0.5.2rc2.dist-info/RECORD,,
|
@@ -1,40 +0,0 @@
|
|
1
|
-
import torch
|
2
|
-
from mooncake_store import MooncakeStore
|
3
|
-
|
4
|
-
|
5
|
-
def test_init_and_warmup():
|
6
|
-
store = MooncakeStore()
|
7
|
-
assert store.store is not None
|
8
|
-
|
9
|
-
|
10
|
-
def test_register_buffer():
|
11
|
-
store = MooncakeStore()
|
12
|
-
tensor = torch.zeros(1024, dtype=torch.float32)
|
13
|
-
store.register_buffer(tensor)
|
14
|
-
|
15
|
-
|
16
|
-
def test_set_and_get():
|
17
|
-
store = MooncakeStore()
|
18
|
-
|
19
|
-
key = ["test_key_" + str(i) for i in range(2)]
|
20
|
-
tensor = torch.arange(256, dtype=torch.float32).cuda()
|
21
|
-
ptrs = [tensor.data_ptr(), tensor.data_ptr()]
|
22
|
-
sizes = [tensor.numel() * tensor.element_size()] * 2
|
23
|
-
|
24
|
-
store.set(key, target_location=ptrs, target_sizes=sizes)
|
25
|
-
store.get(key, target_location=ptrs, target_sizes=sizes)
|
26
|
-
|
27
|
-
|
28
|
-
def test_exists():
|
29
|
-
store = MooncakeStore()
|
30
|
-
keys = ["test_key_0", "non_existent_key"]
|
31
|
-
result = store.exists(keys)
|
32
|
-
assert isinstance(result, dict)
|
33
|
-
assert "test_key_0" in result
|
34
|
-
|
35
|
-
|
36
|
-
if __name__ == "__main__":
|
37
|
-
test_init_and_warmup()
|
38
|
-
test_register_buffer()
|
39
|
-
test_set_and_get()
|
40
|
-
test_exists()
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|