Commit Graph

85 Commits

Author SHA1 Message Date
Simo Lin
38907fe639 refactor(pd-router): extract common patterns to reduce code duplication (#9081) 2025-08-11 13:32:31 -07:00
Simo Lin
6f81a710f7 [pd-router] add retry and circuit breakfor for pd router (#9051) 2025-08-11 05:53:26 -07:00
Simo Lin
067068f271 [router] regular router circuit breaker (#8997) 2025-08-10 21:19:30 -07:00
Simo Lin
ce9cf35327 [router] update pyo3 version to 0.25.1 (#9022) 2025-08-10 06:45:51 -07:00
Simo Lin
473400e452 [router] upgrade kube version to latest (#9018) 2025-08-09 22:49:45 -07:00
Simo Lin
dd665f967f [router] upgrade rand to latest version (#9017) 2025-08-09 22:49:30 -07:00
Simo Lin
7b7e56150e [router] fix radix tree integration issues in PD router (#8982) 2025-08-08 14:47:51 -07:00
Simo Lin
1a8706c8b9 [router] reduce contention, fix double-count race (#8978) 2025-08-08 14:29:14 -07:00
Tony Lu
36bfddecb9 [router] add metrics for worker and policy (#8971)
Signed-off-by: Tony Lu <tonyluj@gmail.com>
2025-08-08 13:41:40 -07:00
Simo Lin
a59cbea92d [router] harden retries + metrics; fix streaming load; header filtering (#8972) 2025-08-08 13:10:14 -07:00
Simo Lin
61a4680494 [router] router circuit breaker core (#8941) 2025-08-08 09:20:22 -07:00
Simo Lin
2e901e892f [router] dedicated prefill HTTP client and request-path optimizations (#8923) 2025-08-07 17:31:45 -07:00
Simo Lin
500b15c960 [router] upgrade router version to 0.1.9 (#8844) 2025-08-07 09:29:12 -07:00
Tien Nguyen
fd05b56750 refactor(sgl-router): Replace once_cell with LazyLock in worker.rs and remove once_cell dependency from Cargo.toml (#8698) 2025-08-07 06:14:03 -07:00
Simo Lin
a69b637014 [router] fix req handling order, improve serialization, remove retry (#8888) 2025-08-06 23:24:39 -07:00
Simo Lin
8c7bb39dfb [router] PD Router Simplification and Reorganization (#8838) 2025-08-05 21:20:38 -07:00
Simo Lin
5d62b56f7e [router] complete router oai spec (#8828) 2025-08-05 18:30:19 -07:00
Simo Lin
354ac43555 [pd-router] Add Configurable Retry Logic for reduce backend pressure (#8744) 2025-08-04 20:42:07 -07:00
Simo Lin
2fa0462c39 [router] introduce dp worker abstraction (#8639) 2025-08-04 06:42:20 -07:00
Simo Lin
828a4fe944 [router] Implement HTTP Dependency Injection Pattern for Router System (#8714) 2025-08-02 19:16:47 -07:00
Simo Lin
6d4fd8826e [router] minor code clean up and and refactoring (#8711) 2025-08-02 13:46:31 -07:00
Simo Lin
ab9b893e61 [bug] limit bootstrap room to to [0, 2^63 - 1] (#8684) 2025-08-01 14:41:01 -07:00
Simo Lin
39decec10b [router] upgrade router version to 0.1.8 (#8645) 2025-07-31 19:00:23 -07:00
Simo Lin
f6f46f4629 [router] add basic usage doc (#8640) 2025-07-31 18:11:48 -07:00
Simo Lin
2886e23dbd [bugfix] fix router python parser for pd urls (#8644) 2025-07-31 18:09:31 -07:00
Michael Yao
061c8959ff Fix typos in py_test/test_launch_server.py (#6227)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
2025-07-31 12:48:47 -07:00
Simo Lin
aee0ef52f5 [router] update router pypi version (#8628) 2025-07-31 11:24:12 -07:00
Simo Lin
66a398f49d [router] migrate router from actix to axum (#8479) 2025-07-30 17:47:19 -07:00
Rui Chen
a730ce8162 [feature] [sgl-router] Add a dp-aware routing strategy (#6869) 2025-07-30 05:58:48 -07:00
Simo Lin
fe6a445d1e [router] improve router logs and request id header (#8415) 2025-07-27 19:30:19 -07:00
Simo Lin
2ab97023e3 [router] add different policies for p node and d node (#8395) 2025-07-27 00:39:20 -07:00
Simo Lin
39fe1e880d [router] add request format unit test (#8300) 2025-07-24 14:30:37 -07:00
Simo Lin
33c4b4d04e [router] add streaming unit test (#8299) 2025-07-24 14:30:27 -07:00
Simo Lin
2f86f3ad62 [router] add endpoint unit test (#8298) 2025-07-23 23:26:44 -07:00
Simo Lin
f6e07f2796 [router] fix pd model completion request (#8303) 2025-07-23 23:18:29 -07:00
Simo Lin
6f8f4aeea4 [router] add common ut infra to mock worker and app (#8295) 2025-07-23 10:07:51 -07:00
Rui Chen
c33499a67b fix: sgl-router remove dead code (#8257) 2025-07-22 08:41:23 -07:00
Simo Lin
9b5de6cb06 [router] upgade router version to 0.1.6 (#8209) 2025-07-20 23:13:20 -07:00
Simo Lin
5c8365a051 [router] add ut for pd router (#8208) 2025-07-20 23:12:52 -07:00
Simo Lin
1fc455e8b6 [router] add ut for pd request, metrics and config (#8184) 2025-07-20 10:53:42 -07:00
Simo Lin
41d33e4736 [router] add ut for worker and errors (#8170) 2025-07-19 14:38:33 -07:00
Charles Chen
f3d9736156 Fix suffix mismatch for the metrics. (#8168)
Signed-off-by: Charles Chen <chenliqian@chenliqian.cn>
2025-07-19 10:11:24 -07:00
Simo Lin
b763cf7e8e [router] allow router to have empty workers (#8160) 2025-07-18 22:09:54 -07:00
Simo Lin
8fcc55cfa1 [router] router metrics cleanup (#8158) 2025-07-18 22:09:17 -07:00
Simo Lin
c8f31042a8 [router] Refactor router and policy traits with dependency injection (#7987)
Co-authored-by: Jin Pan <jpan236@wisc.edu>
Co-authored-by: Keru Yang <rukeyang@gmail.com>
Co-authored-by: Yingyi Huang <yingyihuang2000@outlook.com>
Co-authored-by: Philip Zhu <phlipzhux@gmail.com>
2025-07-18 14:24:24 -07:00
Simo Lin
f2d5c4920e [router] add worker abstraction (#7960) 2025-07-11 20:17:48 -07:00
Simo Lin
4ed57807c2 [bugfix] add pd router policy validation (#7904) 2025-07-09 21:52:06 -07:00
Shuaiyi Zhang
7590f5224b [router] Update metrics when request completes (#7899) 2025-07-09 08:18:09 -07:00
Shuaiyi Zhang
51ae40306a [router] forward stream_options in request (#7860) 2025-07-08 08:03:38 -07:00
Simo Lin
3646f6bb3e [misc] release new router version (#7798) 2025-07-06 22:54:17 -07:00