Commit Graph

84 Commits

Author SHA1 Message Date
Yan Ru Pei ebaf048d16
chore: plumb allowed_worker_ids through RoutingHints (#6580)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-02-25 12:12:53 -08:00
atchernych c916cd42ff
feat: Support epp's "pods" interface in Dynamo fixes [DEP-424] (#6302)
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
2026-02-25 01:54:38 +00:00
Biswa Panda 75fea78797
feat: make KV cache events and routing LoRA-aware (#6517) 2026-02-24 18:35:08 +00:00
Tzu-Ling Kan 80cac7c14b
feat: Remove Component from public (#6403)
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
2026-02-23 22:58:38 +00:00
Yan Ru Pei 038b50d2b6
feat: add standalone KV indexer with query endpoint [DYN-2164] (#6446)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-23 12:12:25 -08:00
Yan Ru Pei fc229004b5
chore: Remove ZmqKvEventListener binding and rework standalone TRT-LLM example to use native Python ZMQ (#6164)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-02-19 04:15:13 +00:00
zhongdaor-nv 815b129126
feat: mm aware routing for vllm (#6235)
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
2026-02-13 21:16:06 -08:00
Yan Ru Pei 14eceb43df
chore: rename KvPushRouter to KvRouter in python + more bindings removal (#6238)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-02-12 23:44:52 -08:00
Yan Ru Pei bc514fbee6
feat: router priority queue (#6010)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
2026-02-13 02:43:17 +00:00
Karen Chung cd6984b951
feat: use RNG when dp routing targets are tied; override no-assume-kv-reuse for decode requests (#6253)
Signed-off-by: Karen Chung <karenc@nvidia.com>
2026-02-12 15:59:37 -08:00
Yan Ru Pei 6a728d1044
chore: remove kv indexers bindings (#6159)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-02-11 20:23:48 +00:00
Yan Ru Pei f46720c996
feat: add router-level Prometheus metrics and centralize request tracking (#6146)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-11 07:36:08 +00:00
Yan Ru Pei 6783bdcaa9
chore: enable local indexers by default, and use normal event plane by default (not jetstream) (#5941)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-02-08 20:48:02 +00:00
Yan Ru Pei 3e41702211
chore: remove and unify bindings in kv.rs (#6016)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-02-06 18:44:46 +00:00
Hongkuan Zhou 0c0336e6ea
feat: Add per-worker Prometheus metrics for router load monitoring (#5842)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
2026-02-04 11:51:43 -08:00
Yan Ru Pei 902eabd9ec
feat: per dp rank gap detection (#5873)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-02-03 03:07:57 +00:00
Biswa Panda 373e76c1ae
feat(lora): Add lora_name tracking to scheduling and sequence management (#5875) 2026-02-03 00:59:09 +00:00
ishandhanani c5f5ab6056
fix: enable DP attention KV events for multi-node deployments (#5589)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: huitianbai <huitianbai@gmail.com>
Co-authored-by: Huitianqi Bai <huitianbai@users.noreply.github.com>
2026-02-02 07:20:29 +00:00
Biswa Panda 1174c819cb
feat: remove deprecated events api (#5778) 2026-01-29 05:48:16 +00:00
Yan Ru Pei fc92fc187b
chore: clean ups in kv-router (#5771)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-01-29 03:20:04 +00:00
Yan Ru Pei feb6d272ac
chore: nuke ForwardPassMetrics (#5531)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-01-23 16:26:01 +00:00
Graham King c5458b9954
chore(router): Remove deprecated best_worker_id and metrics_labels (#5412)
Signed-off-by: Graham King <grahamk@nvidia.com>
2026-01-14 16:20:42 +00:00
Tushar Sharma cf433e6825
chore: update all copyright headers in repo to 2026 (#5130)
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
2026-01-02 22:08:23 +00:00
Yan Ru Pei 0b33c1dfa0
fix: sglang disagg routing fixes and optimizations [DYN-1692] (#5106)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Ishan Dhanani <ishandhanani@gmail.com>
Co-authored-by: Sean SH Choi <sechoi@nvidia.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
2025-12-31 10:55:44 -08:00
Yan Ru Pei f4245c9929
chore: clean up PreprocessedRequest (#5040)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-12-19 23:15:59 +00:00
zhongdaor-nv 481dc6363b
feat: add multimodal support to KV router with standalone trtllm example (#4577)
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
2025-12-18 21:01:45 -08:00
Yan Ru Pei 85b5c808ac
feat: unify per-request metric tracking (#5004)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-12-18 23:59:25 +00:00
Yan Ru Pei c2a29f8045
chore: enable local indexers for sglang and trtllm (#4932)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-12-12 11:41:37 -08:00
Karen Chung 332499458b
feat: worker-local KvIndexer in KvEventPublisher (#4519)
Co-authored-by: Yan Ru Pei <yanrpei@gmail.com>
2025-12-11 23:18:34 +00:00
Yan Ru Pei c61e0dd3cc
chore: merge KvIndexer and ApproxKvIndexer (#4500)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-11-21 09:09:11 -08:00
Kris Hung 2f18b23ee7
chore: Use general engine source for KVBM KV events (#4515) 2025-11-20 14:47:48 -08:00
Waël Boukhobza 2cf427ed8f
fix(router): change prune channel to be mpsc instead of watch, increase max size (#4351)
Signed-off-by: Wael Boukhobza <wawa_wael@live.fr>
2025-11-14 18:19:20 -05:00
Yan Ru Pei 8379b0cd10
feat: kv router should route to available instances (#4225)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-11-13 02:34:58 +00:00
Waël Boukhobza 3ea22fcf39
feat(router): max tree size based pruning (#4057)
Signed-off-by: Wael Boukhobza <wawa_wael@live.fr>
2025-11-12 08:33:49 -08:00
Yan Ru Pei 427ca9aba4
chore: no need for explicit Python::with_gil (#4075)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-11-05 05:41:49 +00:00
Michael Feil defe5de74b
feat: release gil for publisher (#3747)
Signed-off-by: michaelfeil <me@michaelfeil.eu>
2025-11-05 02:17:06 +00:00
Yan Ru Pei cc4c3516bb
feat: mocker disagg (#3833)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-10-28 20:36:02 +00:00
Graham King c78b590134
chore(runtime): Do not expose etcd lease ID (#3915)
Signed-off-by: Graham King <grahamk@nvidia.com>
2025-10-28 16:20:25 +00:00
Graham King 7731b0245c
chore: Use KeyValueStoreManager instead of etcd::Client (#3822)
Signed-off-by: Graham King <grahamk@nvidia.com>
2025-10-23 14:09:58 -04:00
Michael Feil 681951d4e6
feat: python gil release for radix tree + dump_tree_as_events in python (#3748)
Signed-off-by: michaelfeil <me@michaelfeil.eu>
Co-authored-by: Yan Ru Pei <yanrpei@gmail.com>
2025-10-22 01:41:35 +00:00
Yan Ru Pei e01c6e99bd
feat: bake prefill router into frontend, supporting vllm for now (#3762)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-10-21 15:43:02 -07:00
Yan Ru Pei 4c207e0c8c
chore: remove kv metrics scraping and aggregation (#3701)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-10-17 10:58:48 -07:00
Yan Ru Pei f978f4d1d6
feat: dp rank routing (#3597)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-10-16 01:48:27 +00:00
Yan Ru Pei b5e762b2b8
feat: remove stale workers on snapshot + some refactoring (#3589)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-10-13 21:36:09 +00:00
Yan Ru Pei c3fcfdd6e3
chore: consolidations of KvPushRouter bindings and usage examples (#3543)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Signed-off-by: Yan Ru Pei <yanrpei@gmail.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
2025-10-11 05:47:25 +00:00
Yan Ru Pei 30610e7371
feat: use KvPushRouter for prefill router (#3401)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-10-03 18:21:48 -07:00
Yan Ru Pei 9b9536d0d7
feat: make prefill router general (#3329)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-09-30 20:38:47 -07:00
Yan Ru Pei d354763c40
fix: python bindings for router should register to etcd as well (#3302)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-09-30 12:38:56 -07:00
Alec 5bb7490448
chore: bump vllm version to 0.10.2 (#3180)
Signed-off-by: Alec <aflowers@nvidia.com>
Signed-off-by: Alec <35311602+alec-flowers@users.noreply.github.com>
Signed-off-by: krishung5 <krish@nvidia.com>
Co-authored-by: Kris Hung <krish@nvidia.com>
2025-09-26 04:01:57 +00:00
Yan Ru Pei 031590fc14
feat: vllm prefill router (#3155)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-09-22 16:38:56 -07:00