Commit Graph

1280 Commits

Author SHA1 Message Date
Lianmin Zheng
1929c06762 Simplify prometheus metrics (#1981)
Co-authored-by: Mohit Reddy <mohitreddy1996@users.noreply.github.com>
2024-11-10 04:39:32 -08:00
Huanzhi (Hans) Mao
ed53ac84b4 Specify zmq Version Requirement (#1982) 2024-11-10 01:32:07 -08:00
Lianmin Zheng
520f0094e4 [CI] balance unit tests (#1977) 2024-11-09 16:46:14 -08:00
Lianmin Zheng
9c939a3d8b Clean up metrics code (#1972) 2024-11-09 15:43:20 -08:00
Lianmin Zheng
549e8b8366 [Minor] Fix a typo in test_torchao.py (#1976) 2024-11-09 15:07:27 -08:00
Lianmin Zheng
a1f32867ca Update pr-test-rust.yml to add a "finish" step (#1975) 2024-11-09 13:53:35 -08:00
Lianmin Zheng
760552e068 Update README.md (#1974) 2024-11-09 11:32:13 -08:00
Kursat Aktas
d9aada9db1 Introducing SGLang Guru on Gurubase.io (#1745) 2024-11-09 11:29:26 -08:00
Enrique Shockwave
f11eb90fe4 Initialize model_worker_batch variable (#1973) 2024-11-09 11:28:02 -08:00
Yudi Xue
95a4ed129a Fix metrics (#1963) 2024-11-08 23:21:11 -08:00
leishaoSC
d1150e9a00 Updated Instructions on Profiling SGLang Infer System with AMD GPUs (#1966)
Co-authored-by: wunhuang <wunhuang@amd.com>
2024-11-08 23:19:03 -08:00
Chayenne
e3126e3c5f Update README.md's Slack invitation link (#1962) 2024-11-08 11:46:25 -08:00
Lianmin Zheng
a509552087 [minor] Improve code style and compatibility (#1961) 2024-11-08 02:19:41 -08:00
Lianmin Zheng
7ef0084b0d Add sentence_transformers to CI dependency (#1958) 2024-11-08 01:21:29 -08:00
HAI
f9a377f650 [Release, ROCm] release ROCm docker build for AMD MI GPUs (#1957) 2024-11-08 00:14:15 -08:00
aqweteddy
4ade15dd32 Adjust reward model's score module and pooler module order for reducing computation (#1956) 2024-11-08 00:10:54 -08:00
Lianmin Zheng
8dc84da084 Remove the useless to_srt_kwargs (#1955) 2024-11-07 23:15:08 -08:00
aqweteddy
f16eb15d0d Gemma2 reward model support (#1954) 2024-11-07 22:42:27 -08:00
Yudi Xue
5bc2508b80 Monitoring documentation (#1933) 2024-11-07 22:14:16 -08:00
Lianmin Zheng
a71a44f203 Update setup_github_runner.md (#1952) 2024-11-07 19:20:47 -08:00
Lianmin Zheng
691808d587 Add a timeout for execute-notebook.yml (#1951) 2024-11-08 10:28:29 +08:00
HAI
d32fba2a4d [ENV, ROCm] update environment settings (#1939) 2024-11-07 18:24:36 -08:00
HAI
67c424cce3 [Performance, Triton Kernel Args] extend_attention, optimize kern args to _fwd_kernel (#1941) 2024-11-07 18:24:02 -08:00
Lianmin Zheng
1ae270c5d0 [Doc] fix docs (#1949) 2024-11-07 18:20:41 -08:00
Chayenne
c77c1e05ba fix black in pre-commit (#1940) 2024-11-08 07:42:47 +08:00
HAI
dca87ec348 [Docs] fix 404 - Contributor Guide (#1942) 2024-11-07 16:50:45 +08:00
Austin Liu
4b1d7a2583 Add Rust Router Python Binding (#1891)
Signed-off-by: Austin Liu <austin362667@gmail.com>
Co-authored-by: ByronHsu <byronhsu1230@gmail.com>
2024-11-06 18:08:30 -08:00
Xuehai Pan
a5e0defb5a minor: Add basic editorconfig and pre-commit hooks to enforce style for whitespaces (#1926) 2024-11-06 13:46:04 +00:00
Byron Hsu
96766101b4 [rust] refactor server and router (#1922) 2024-11-06 00:02:02 -08:00
Lzhang-hub
a146d9990e support prometheus metrics (#1853)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
2024-11-05 20:42:53 -08:00
Lianmin Zheng
f5113e50ae [Doc] improve relative links and structure (#1924) 2024-11-05 01:12:10 -08:00
Chayenne
02755768d3 Change judge to classify & Modify make file (#1920) 2024-11-04 23:53:44 -08:00
Byron Hsu
463d56bf44 Update CODEOWNERS (#1916) 2024-11-05 09:13:41 +08:00
Byron Hsu
530ff541cf [router] Impl radix tree and set up CI (#1893)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2024-11-04 10:56:52 -08:00
HAI
3cd2809277 [Docs, ROCm] update install to cover ROCm with MI GPUs (#1915) 2024-11-04 17:40:57 +08:00
Chayenne
704f8e8ed1 Add Reward API Docs etc (#1910)
Co-authored-by: Chayenne <zhaochenyang@g.ucla.edu>
2024-11-03 22:33:03 -08:00
Lianmin Zheng
1853c3523b Fix regex docs (#1909) 2024-11-03 14:18:16 -08:00
Lianmin Zheng
65859754f1 Release v0.3.5 (#1908) 2024-11-03 13:48:11 -08:00
Lianmin Zheng
2ce32db6fb Let reward model take text inputs instead of message lists (#1907)
Co-authored-by: Kyle Corbitt <kyle@corbt.com>
2024-11-03 13:27:12 -08:00
Yineng Zhang
793b79dbe9 feat: support truss endpoint for benchmark serving (#1906) 2024-11-03 12:56:10 -08:00
Iñaki Arango
1363b51983 Escape backwards slash (#1902) 2024-11-03 12:27:11 -08:00
Lianmin Zheng
0abbf289a8 Unify the model type checking (#1905) 2024-11-03 12:25:39 -08:00
Lianmin Zheng
c17c578108 Simplify tokenizer manager (#1904) 2024-11-03 08:38:26 -08:00
Jani Monoses
916b3cdddc Allow passing dtype and max_new_tokens to HF reference script (#1903) 2024-11-03 08:24:37 -08:00
Lianmin Zheng
838dcda162 Simplify tokenizer manager (#1899) 2024-11-03 03:52:38 -08:00
Lianmin Zheng
efbc116a0f Do not use longest prefix matching when #queue-req is large (#1896) 2024-11-03 01:45:20 -07:00
Chayenne
6aed0445ed turn off log (#1895) 2024-11-03 00:19:12 -07:00
Chayenne
908dd7f9aa Add engine api (#1894) 2024-11-02 22:03:38 -07:00
Chayenne
f4cd804073 Fix ci and link error (#1892)
Co-authored-by: Chayenne <zhaochenyang@g.ucla.edu>
2024-11-02 19:08:49 -07:00
Lianmin Zheng
be7986e005 Fix docs (#1890) 2024-11-02 13:26:32 -07:00