53 Commits
Author SHA1 Message Date
2032f3a071 [Router] Abort the engine when a client disconnects mid-request (#39461)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Kan Wu <wukanustc@gmail.com>
2026-09-22 12:35:56 +08:00
Kan Wu 59a723ef1e [sgl-router] refactor - SLO ordering for bucket selection (#40292) 2026-09-22 11:16:10 +08:00
Kan Wu 27f796ca6c [sgl-router] Fix readiness, IPv6 discovery, logging, and model validation (#40604) 2026-09-22 11:13:06 +08:00
Kan WuandShangming Cai 008470abd8 [sgl-router] Bound streaming lifetimes and release guards on idle disconnect (#40391)
Co-authored-by: Shangming Cai <csmthu@gmail.com>
2026-09-21 10:07:07 -07:00
Kan Wu 0f6761b54f [sgl-router] Add SGLang-compatible DeepSeek V4.1 Flash rendering (#40532) 2026-09-21 18:35:09 +08:00
0abb251a20 [sgl-router] Match DeepSeek V4 rendering to SGLang (#40530)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
2026-09-21 17:56:41 +08:00
Kan WuandClaude Fable 5.1 2016f5e7a1 [sgl-router] Add Kimi-K3 rendering with SGLang parity (#40390)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-21 17:38:49 +08:00
630b1ef322 [sgl-router] Fix reorg admission proxy test build after BucketResolver::new (#40537)
Co-authored-by: Kan Wu <wukanustc@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-21 16:42:29 +08:00
Kan WuandClaude Fable 5.1 a9871012ac [sgl-router] refactor - generalized admission policy definitions (#40271)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-21 16:26:30 +08:00
Kan WuandClaude Fable 5.1 fcb080bd40 [sgl-router] refactor - cache-aware policy (#40366)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-21 13:53:57 +08:00
Kan WuandClaude Fable 5.1 4027740569 [sgl-router] refactor - session-aware policy (#40379)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-20 17:22:36 -07:00
Kan WuandClaude Fable 5.1 aedda8377e [sgl-router] refactor - layout BucketResolver, Bucket, EngineGroup and implement PowerOfTwo (#40241)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-20 16:57:07 -07:00
Kan WuandClaude Fable 5.1 4a9dc5c4af [sgl-router] refactor - move policy-required states under src/state (#40272)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-20 16:49:23 -07:00
aed3fb1cdd [Router] Log every request at one site; derive its outcome from the final status (3/3) (#39465)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
2026-09-19 03:11:00 +08:00
6de4666e43 [Router] Derive error status from a failure class; preserve the worker's status (1/3) (#39463)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-18 16:32:45 +08:00
3bf243d6a9 [Router] Shard the cache-aware KV tree by chain root (#39167)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
2026-09-18 15:00:17 +08:00
e4cbb28ea1 [router] Improve SGLang chat render parity (#39133)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
2026-09-17 23:53:40 +08:00
Kan WuandClaude Fable 5.1 3ce7e2a29f [sgl-router] Render chat prompts with dynamo-render (#38983)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-17 15:57:20 +08:00
b02e16a895 [Router] Fleet-wide sampling contract 3/3: splice injection without re-serializing (#39002)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 09:59:48 -07:00
3e03879f68 [Router] Drain readiness before SIGTERM shutdown so k8s deregisters the pod first (#39016)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 09:59:26 -07:00
Kan WuandClaude Fable 5.1 ad94978adf [sgl-router] Rename chat encoder to chat formatter (#39459)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-16 08:46:11 -07:00
7835f1de9a [Router] Add the shutdown-drain configuration surface (#39015)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 00:26:50 -07:00
e2d56bbbfc [Router] Bound the e2e worker memory budget so prefill graph capture stops OOMing (#39713)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 00:13:09 -07:00
d634320e48 [Router] Count open HTTP exchanges until their response body finishes (#39014)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 00:04:38 -07:00
afde31a2f5 [router] Speak cleartext h2c on both edges: serve it inbound, forward it outbound (#39006)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-15 22:30:31 -07:00
c1f5b4736a [Router] Add --worker-queue-limit: stop sending cache-affinity traffic to a queueing worker (#39168)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 13:24:48 +08:00
5f17e3a75f [Router] Fleet-wide sampling contract 1/3: the config surface (#39000)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-15 21:39:06 -07:00
63845a1bb2 [router] Resolve a wire protocol per worker at registration (#39004)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-15 16:54:37 -07:00
fb91baedab [Router] Real-GPU e2e coverage for storage-tier-aware cache routing (3/4) (#39110)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-15 15:48:51 -07:00
ishandhanani 3f871a246c feat(agent sessions): attribute stored KV cache blocks to sessions (#37482)
Signed-off-by: Ishan Dhanani <ishandhanani@gmail.com>
2026-09-14 21:34:49 -07:00
45b511b2ef [Router] Honor KV-event storage tiers in the cache-aware tree (1/4) (#39108)
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-14 21:18:15 -07:00
Kan WuandClaude Fable 5.1 e89d8facab [sgl-router] Prepare dynamo-render dependencies (#39457)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-14 19:08:16 -07:00
Kan Wu f539c1fc65 [sgl-router] Stream outcome observability for 2xx SSE streams (#38737) 2026-09-13 19:46:44 -07:00
Vincent Gao 8e7deb329e [Router] Preserve global cache affinity with bucket routing (#38814)
Signed-off-by: Vincent Gao <vincentbo@linux.alibaba.com>
2026-09-11 17:41:27 +08:00
5bebe7a033 [Router] Add bucket-aware policy domains and native cache indexing (#38108)
Signed-off-by: Vincent Gao <vincentbo@linux.alibaba.com>
Co-authored-by: inkcherry <mingzhi.liu@amd.com>
Co-authored-by: yangbodong22011 <13137470+yangbodong22011@users.noreply.github.com>
2026-09-06 19:47:51 +08:00
ecd97de1fc [Router] Add load-aware prefill admission and bounded policy proposals (#37843)
Signed-off-by: Vincent Gao <vincentbo@linux.alibaba.com>
Co-authored-by: Kangyan Zhou <zky314343421@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
2026-09-05 11:53:26 +08:00
Vincent Gaoandinkcherry 54cadad151 [Router] Add composable scoring and eligibility policies (#37731)
Co-authored-by: inkcherry <mingzhi.liu@amd.com>
2026-09-04 00:01:41 +08:00
Alex NailsandAlison Shao 28262c20df [CI][RFC] Replace black-jupyter with ruff-format (#37210)
Co-authored-by: Alison Shao <a.shao@wustl.edu>
2026-09-02 19:46:08 -07:00
360d10d6bc [Feature] Add process-local in-memory KV indexer and Router integration (#33370)
Co-authored-by: Wu, Yutong <yutong.wu@amd.com>
Co-authored-by: TianDi101 <ditian12@amd.com>
Co-authored-by: Zhangheng <hzh0425@apache.org>
2026-08-20 10:45:35 +08:00
Xiaoyu Zhang b276a9acee chore: cleanup garbage code (#29770) 2026-07-02 16:14:01 +08:00
Liangsheng Yin cd6dedf972 [router] Count requests/responses at the HTTP edge for true intake (#29467) 2026-06-26 21:21:41 -07:00
Kangyan-ZhouandClaude Opus 4.8 364bf976be [router] Tokenize prompt once at ingress; forward input_ids to the engine (all policies) (#28744)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 16:07:17 -07:00
Kangyan-ZhouandClaude Opus 4.8 abf7011cdd [router] Raise chat body cap to 5 MiB for long contexts (#28742)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 15:50:34 -07:00
Jia-Wei Jiang a88ba6cc0b [Fix] Reduce power of two to constant time (#28228)
Signed-off-by: JiangJiaWei1103 <waynechuang97@gmail.com>
2026-06-14 23:25:22 -07:00
Kangyan-ZhouandClaude Opus 4.8 c0dfe4c8ec [router] Reconcile workers that registered without resolving model_ids (#27980)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 18:47:50 -07:00
Kangyan-ZhouandClaude Opus 4.8 21647f1f5d [router] Apply chat template before cache-aware hashing (fix overlap=0 on chat traffic) (#27386)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-10 10:27:54 -07:00
Kangyan-ZhouandClaude Opus 4.8 0c7faf01fb test(sgl-router): cover sticky scale-up no-redistribution e2e (#27742)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-10 08:54:31 -07:00
Kangyan-ZhouandClaude Opus 4.8 badab6b136 [router] Add request/TTFT/worker metrics + Grafana dashboard to experimental sgl-router (#27591)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-09 07:25:56 -07:00
Matt Van HornandMatt Van Horn 317fc6a9dd refactor: replace oversized 1.3MB tiny_tokenizer.json fixture with a genuinely tiny byte-level BPE fixture (#27235)
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
2026-06-08 17:40:32 -07:00
Kangyan-ZhouandClaude Opus 4.8 6bc3953b48 feat(agentic router): add sticky-session routing policy (#27394)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-07 20:05:27 -07:00