sglang 0.1.19__py3-none-any.whl → 0.1.20__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 +1 -1
- sglang/bench_latency.py +7 -3
- sglang/global_config.py +21 -17
- sglang/srt/layers/radix_attention.py +14 -37
- sglang/srt/layers/token_attention.py +2 -9
- sglang/srt/managers/controller/cuda_graph_runner.py +172 -0
- sglang/srt/managers/controller/infer_batch.py +242 -34
- sglang/srt/managers/controller/model_runner.py +56 -283
- sglang/srt/managers/controller/tp_worker.py +8 -6
- sglang/srt/memory_pool.py +33 -6
- sglang/srt/server.py +1 -0
- sglang/srt/server_args.py +10 -4
- {sglang-0.1.19.dist-info → sglang-0.1.20.dist-info}/METADATA +1 -1
- {sglang-0.1.19.dist-info → sglang-0.1.20.dist-info}/RECORD +17 -16
- {sglang-0.1.19.dist-info → sglang-0.1.20.dist-info}/WHEEL +1 -1
- {sglang-0.1.19.dist-info → sglang-0.1.20.dist-info}/LICENSE +0 -0
- {sglang-0.1.19.dist-info → sglang-0.1.20.dist-info}/top_level.txt +0 -0
@@ -1,7 +1,7 @@
|
|
1
|
-
sglang/__init__.py,sha256=
|
1
|
+
sglang/__init__.py,sha256=M8FawCAF4B2Fbj3fJTm3kLu0YDgYRVC7MMRcBS_QwM0,1116
|
2
2
|
sglang/api.py,sha256=W_FO5JTrW9I-DoGx2O8cLhcSA6LJqgplrOIqAX-ryNA,5560
|
3
|
-
sglang/bench_latency.py,sha256=
|
4
|
-
sglang/global_config.py,sha256=
|
3
|
+
sglang/bench_latency.py,sha256=r2F3TcxlvpCz4hCiK41dnmpxxU_sS37x1F7md5HJNIQ,10410
|
4
|
+
sglang/global_config.py,sha256=8ImBH5mECeCFVi8TtewNRFKHlFCrYG3qof5cSS7aZUY,1670
|
5
5
|
sglang/launch_server.py,sha256=X8TX6M-tv9JWHJkWnJskYNc0IZBooecI_yzpBHVf5KU,364
|
6
6
|
sglang/launch_server_llavavid.py,sha256=cxGJICBTYVgHVNy7NWwitY7VXt11kEnh7npkcB-iRf8,1115
|
7
7
|
sglang/utils.py,sha256=arJuwOAEX445M2NL9SAOi6jBNu0-cfU04PLAr-hIH3U,8168
|
@@ -21,14 +21,14 @@ sglang/lang/tracer.py,sha256=QcslAObEjepk8XmiqCobwzWaDpihofEQXjeRs_3B8NQ,8282
|
|
21
21
|
sglang/srt/conversation.py,sha256=kuMrdYtcpy2F7qACMEYdD1CniP6HHNRSvhqVZe8jj_w,15522
|
22
22
|
sglang/srt/flush_cache.py,sha256=SJsbZnmDhH-gb9ch3hIwnI_nuwaOLlKvlXADyLBGENk,403
|
23
23
|
sglang/srt/hf_transformers_utils.py,sha256=H3YnLtx05q65A1tn1JWNZOUhMtq6jANRhhMo6JJr6mg,10728
|
24
|
-
sglang/srt/memory_pool.py,sha256=
|
24
|
+
sglang/srt/memory_pool.py,sha256=3ftXky9baIrgDzYJAywBOO2YOJXQ7RgCG-usMFK6QaQ,4418
|
25
25
|
sglang/srt/mm_utils.py,sha256=OptgAHDX-73Bk4jAdr2BOAJtiEXJNzPrMhaM-dy275c,8889
|
26
26
|
sglang/srt/model_config.py,sha256=lZu1D-XLVMETHS6FBMoPn8Uowa9QFGe95d3SuWrr2q8,5282
|
27
27
|
sglang/srt/openai_api_adapter.py,sha256=iw-FquXQeM2Z4nxOoYGFPjTkIdgA8rQkh_IcmJRy-R0,15143
|
28
28
|
sglang/srt/openai_protocol.py,sha256=-KJsGx2izL3Fc5EhOGi9PAXExuaq-DKRk0UlNjts11E,5348
|
29
29
|
sglang/srt/sampling_params.py,sha256=dQbVr7JmTJ9JEn_sy3clB56yT9kyr9ldWFZ-GaNXOy0,3023
|
30
|
-
sglang/srt/server.py,sha256=
|
31
|
-
sglang/srt/server_args.py,sha256=
|
30
|
+
sglang/srt/server.py,sha256=iVrP9G8ljMGY8Tbg64RrPwbcmyl6og66fBatdXIx6TE,13268
|
31
|
+
sglang/srt/server_args.py,sha256=NPsNq_FuOU4cQVne4XoqHNoeQgGDCwBkAqUKn3joMDk,12492
|
32
32
|
sglang/srt/utils.py,sha256=e-yPzqDMCGsPgEf4TIe7CEh44lsKpZnclsrMtBggS_Y,19366
|
33
33
|
sglang/srt/constrained/__init__.py,sha256=5LB3_mDTMW6wcRkFA5J2Rd5HPHHEKRyiELhe4gtlBYM,1472
|
34
34
|
sglang/srt/constrained/base_cache.py,sha256=QQjmFEiT8jlOskJoZobhrDl2TKB-B4b1LPQo9JQCP_w,1405
|
@@ -38,19 +38,20 @@ sglang/srt/layers/context_flashattention_nopad.py,sha256=bENdVltDozccR5mLY_CcYDj
|
|
38
38
|
sglang/srt/layers/extend_attention.py,sha256=sVd94ViwwQaQDuE94sPMg6Ac6VOp7nX80hFol8qr85Q,13008
|
39
39
|
sglang/srt/layers/fused_moe.py,sha256=uyrbCaIHioq3G00xQUrCo53hYDoHzk5rep3Eji3oQiQ,20258
|
40
40
|
sglang/srt/layers/logits_processor.py,sha256=RCHjWxlKlB_Mc2iOMHQKvKN9gjqg4oqgodS6gr3qCbA,9672
|
41
|
-
sglang/srt/layers/radix_attention.py,sha256=
|
42
|
-
sglang/srt/layers/token_attention.py,sha256=
|
41
|
+
sglang/srt/layers/radix_attention.py,sha256=2WgUw39eC2wv61OcGimnSf-Jps4M7mAO5hqomszukvY,5735
|
42
|
+
sglang/srt/layers/token_attention.py,sha256=skkKJCNblFDP7Vqc9oGgK6493A50r6sOHZlPXFfokVM,8667
|
43
43
|
sglang/srt/managers/detokenizer_manager.py,sha256=2oYNtYrSwtfu8G-QcFz_vZK6Buq-eHuZGg9VpxVhYOI,3492
|
44
44
|
sglang/srt/managers/io_struct.py,sha256=aCI4yYtKoioP459lWRN8kqVf4tvYYr_IhZaSnvJylgY,4533
|
45
45
|
sglang/srt/managers/tokenizer_manager.py,sha256=h5nOR8NHCwEm52wiL-ZA1hoM_pvMuyG0j7Zj1h7aMxk,14898
|
46
|
+
sglang/srt/managers/controller/cuda_graph_runner.py,sha256=Z-BbHyMupRYU0W844F75Puiuk3MIyKD2grqK-GpE2qk,6691
|
46
47
|
sglang/srt/managers/controller/dp_worker.py,sha256=ES3-jyxGfHzpgVoXub_3qjVygwfWYWpfN4vuVWU23Gs,3675
|
47
|
-
sglang/srt/managers/controller/infer_batch.py,sha256=
|
48
|
+
sglang/srt/managers/controller/infer_batch.py,sha256=ZZEAsh5UoeTDOyrNiRmRYsivUCoI-pjtQVra3N0x2a8,33071
|
48
49
|
sglang/srt/managers/controller/manager_multi.py,sha256=Z0a-iZzqk8T2Xl7ak2DgE9j00GA6Eb0XoNVx7UlxKa4,6630
|
49
50
|
sglang/srt/managers/controller/manager_single.py,sha256=5c33d1jPgOtys5gmfZe79UD7aXrsV--1Yq9Yc24bh1g,3469
|
50
|
-
sglang/srt/managers/controller/model_runner.py,sha256=
|
51
|
+
sglang/srt/managers/controller/model_runner.py,sha256=hql_1aaSvsq1-AQTITUmyPIHd6RZAwXTBHC3QLLtbho,13244
|
51
52
|
sglang/srt/managers/controller/radix_cache.py,sha256=fMqIm1fTvufI9I_QMoFLfQMkSUWp8VN4wh3-63KJUL0,8193
|
52
53
|
sglang/srt/managers/controller/schedule_heuristic.py,sha256=_ne7W2mrpuO794uh5tYLR3q6XBbgTMdNmE6VpzY1sJE,2312
|
53
|
-
sglang/srt/managers/controller/tp_worker.py,sha256=
|
54
|
+
sglang/srt/managers/controller/tp_worker.py,sha256=_jqg5RyMarrzD3SJY-Qs5GaLfnzv2pnzI8_BySmmRos,31926
|
54
55
|
sglang/srt/models/chatglm.py,sha256=BU0rdp-GCUZcmctBYFFo6i5s5XOUJCQbr-v4EQjwJKo,13275
|
55
56
|
sglang/srt/models/commandr.py,sha256=hHsNQWi0X8rNL7_gpcoUxQxdhxtvx5_RVx8u6cLzqYQ,13606
|
56
57
|
sglang/srt/models/dbrx.py,sha256=lv0nXFGJnmv6toUBRv7q7M1ZTrI3VACrvLBKHA6xdjE,14074
|
@@ -74,8 +75,8 @@ sglang/test/test_conversation.py,sha256=1zIrXcXiwEliPHgDAsqsQUA7JKzZ5fnQEU-U6L88
|
|
74
75
|
sglang/test/test_openai_protocol.py,sha256=eePzoskYR3PqfWczSVZvg8ja63qbT8TFUNEMyzDZpa8,1657
|
75
76
|
sglang/test/test_programs.py,sha256=g80P0QWO8Jv_87onTCsvJ-2MgSh7I6_lzcfdm43JlNY,13616
|
76
77
|
sglang/test/test_utils.py,sha256=Mjn2btfmEQQ7rpsLfNo6VugXCPzUmRpNhssWvxevN4s,11038
|
77
|
-
sglang-0.1.
|
78
|
-
sglang-0.1.
|
79
|
-
sglang-0.1.
|
80
|
-
sglang-0.1.
|
81
|
-
sglang-0.1.
|
78
|
+
sglang-0.1.20.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
|
79
|
+
sglang-0.1.20.dist-info/METADATA,sha256=0m4UL_uHZotvQ2fIohPKob2f-HQev5BJHhEUWUEcqQ4,30262
|
80
|
+
sglang-0.1.20.dist-info/WHEEL,sha256=Z4pYXqR_rTB7OWNDYFOm1qRk0RX6GFP2o8LgvP453Hk,91
|
81
|
+
sglang-0.1.20.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
82
|
+
sglang-0.1.20.dist-info/RECORD,,
|
File without changes
|
File without changes
|