Commit Graph

60 Commits

Author SHA1 Message Date
Simo Lin
9d68bdb240 [router] Add Rust Binary Entrypoint for SGLang Router (#9089) 2025-08-11 21:37:36 -07:00
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
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
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
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
f6e07f2796 [router] fix pd model completion request (#8303) 2025-07-23 23:18:29 -07:00
Rui Chen
c33499a67b fix: sgl-router remove dead code (#8257) 2025-07-22 08:41:23 -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
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
ea3e7ffec7 [bugfix] Fix sgl-router get_server_info endpoint compatibility issue (#7813) 2025-07-06 19:52:57 -07:00
Zilin Zhu
82f021e22e [router] add --log-level to sgl-router (#6512) 2025-07-02 19:33:04 -07:00
Simo Lin
e3f9b54819 [bugfix] fix runtime dropping panic in editable (#7628) 2025-06-29 15:38:28 -07:00
finetune
b3cff3651e Fix sgl-router startup crash (#7619) 2025-06-29 14:41:34 -07:00
Simo Lin
c071198c1d [router] add centralized configuration module for sgl-router (#7588) 2025-06-27 15:42:02 -07:00
Simo Lin
30f2a44a96 [misc] Add PD service discovery support in router (#7361) 2025-06-22 17:54:14 -07:00
Simo Lin
09ae5b20f3 Merge PDLB (Prefill-Decode Load Balancer) into SGLang Router (#7096) 2025-06-19 02:28:15 +08:00
Arthur Cheng
ff91474825 [Router] Fix k8s Service Discovery (#6766)
Co-authored-by: Simo Lin <linsimo.mark@gmail.com>
2025-06-02 16:57:23 -07:00
Chao Yang
1a39979993 Sgl-router Prometheus metrics endpoint and usage track metrics (#6537) 2025-05-24 22:28:15 -07:00
Zilin Zhu
669caa0a3f [router] support http2 in router (#6487) 2025-05-21 01:42:45 -07:00
Zilin Zhu
e3bed74afb [router] Add /list_workers endpoint to router (#6366) 2025-05-17 09:49:02 -07:00
applesaucethebun
2ce8793519 Add typo checker in pre-commit (#6179)
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
2025-05-11 12:55:00 +08:00
Simo Lin
771669cbe0 [fix]: PyO3 macOS linking and consolidate on tracing for logging 2025-04-29 11:26:38 -07:00