Commit Graph
117 Commits
Author SHA1 Message Date
Or Ozeri c280066f9d [v1] Move block_hashes from KVCacheManager to Request.block_hashes (#19728)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
2025-08-15 16:52:52 -07:00
Cyrus Leung 19b927e52d [Core] Use individual MM items in P0/P1 cache and model runner (#22570)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-13 07:18:07 -07:00
+10 08b751ba74 Implicit language-model-only mode via limit-mm-per-prompt (#22299)
Signed-off-by: Roger Wang <hey@rogerw.me>
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
Signed-off-by: Shu Wang <shuw@nvidia.com>
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: XIn Li <xinli@nvidia.com>
Signed-off-by: Junhao Li <junhao@ubicloud.com>
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
Signed-off-by: zitian zhao <zitian.zhao@tencentmusic.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: iAmir97 <Amir.balwel@embeddedllm.com>
Signed-off-by: iAmir97 <71513472+iAmir97@users.noreply.github.com>
Signed-off-by: Linkun <github@lkchen.net>
Co-authored-by: Ning Xie <andy.xning@gmail.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Andrew Sansom <andrew@protopia.ai>
Co-authored-by: Zhiyu <zhiyuc@nvidia.com>
Co-authored-by: Shu Wang <shuw@nvidia.com>
Co-authored-by: XIn Li <xinli@nvidia.com>
Co-authored-by: Junhao Li <streaver91@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Yuxuan Zhang <2448370773@qq.com>
Co-authored-by: ZiTian Zhao <zitian.zhao@tencentmusic.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
Co-authored-by: iAmir97 <71513472+iAmir97@users.noreply.github.com>
Co-authored-by: iAmir97 <Amir.balwel@embeddedllm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Hong Hanh <hanh.usth@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: lkchen <github@lkchen.net>
2025-08-08 22:21:40 -07:00
Cyrus Leung 766bc8162c [Core] Store only the keys for multi-modal data in P0 (#22198)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-07 01:45:04 -07:00
Nick Hill 8d524ce79f [BugFix] Improve internal DP load balancing (#21617)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-08-01 19:45:27 -07:00
Nick Hill 881e1af43a [BugFix] Harden distributed DP startup (#21538)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-08-01 21:40:45 +00:00
wuhang e6680f9e25 [Bugfix] Add log prefix in non-dp mode engine core (#21889)
Signed-off-by: wuhang <wuhang6@huawei.com>
2025-08-01 09:04:16 +00:00
Zebing Lin ca9e2be3ed [Core] Move EngineCoreRequest to Request conversion out of EngineCore (#21627)
Signed-off-by: linzebing <linzebing1995@gmail.com>
2025-07-30 15:00:54 -07:00
Nick Hill 56bd537dde [Misc] Support more collective_rpc return types (#21845)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-30 10:20:20 -07:00
633WHUandchiliu 5c765aec65 [Bugfix] Fix TypeError in scheduler when comparing mixed request_id types (#21816)
Signed-off-by: chiliu <chiliu@paypal.com>
Co-authored-by: chiliu <chiliu@paypal.com>
2025-07-30 08:54:44 -07:00
Nick Hill 7234fe2685 [Misc] Rework process titles (#21780)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-29 05:14:47 +00:00
Maximilien de BayserandRussell Bryant 1cd6eaba54 Support encoder-only models without KV-Cache (#21270)
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
2025-07-26 21:09:52 +08:00
Cyrus Leung 46d81d6951 [V1] Get supported tasks from model runner instead of model config (#21585)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-07-25 05:36:45 -07:00
Chauncey 6da0078523 [Feat] Allow custom naming of vLLM processes (#21445)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-07-24 03:15:23 -07:00
Rui Qiao 73e3949d07 [Misc] Improve comment for DPEngineCoreActor._set_cuda_visible_devices() (#21501)
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2025-07-24 03:13:40 -07:00
11ef7a611e [BugFix] Set CUDA_VISIBLE_DEVICES before spawning the subprocesses (#21211)
Signed-off-by: Yinghai Lu <yinghai@thinkingmachines.ai>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Rui Qiao <ruisearch42@gmail.com>
2025-07-23 21:44:04 -07:00
Woosuk Kwon dc2f159f8a Dump input metadata on crash for async scheduling (#21258)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-07-23 21:10:30 -07:00
d5b981f8b1 [DP] Internal Load Balancing Per Node [one-pod-per-node] (#21238)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2025-07-23 20:57:32 -07:00
Rui Qiao 217937221b Elastic Expert Parallel Initial Support (#20775)
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2025-07-18 17:46:09 -07:00
Cyrus Leung 45badd05d0 [Core] Set pooling params based on task and model (#21128)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-07-18 05:41:17 -07:00
Christian Pinto 4ffd963fa0 [v1][core] Support for attention free models (#20811)
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
2025-07-15 14:20:01 +00:00
Nick Hill 657f2f301a [DP] Support external DP Load Balancer mode (#19790)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-02 10:21:52 -07:00
Nick Hill 8619e7158c [BugFix] Fix multi-node offline data parallel (#19937)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-06-24 12:45:20 -07:00
Maximilien de Bayserand22quinn 799397ee4f Support embedding models in V1 (#16188)
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
2025-06-18 21:36:33 -07:00
Isotr0py 1173804dca [Bugfix] Fix TP inference for Flex attention backend (#19657)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-06-16 11:21:37 +00:00
Nick Hill ee35e96ac3 [BugFix] Don't catch BaseException when dumping execute_model errors (#19626)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-06-16 11:01:08 +00:00
Simon Mo 02f0c7b220 [Misc] Add SPDX-FileCopyrightText (#19100)
Signed-off-by: simon-mo <simon.mo@hey.com>
2025-06-03 11:20:17 -07:00
Rui Qiao bdce64f236 [V1] Support DP with Ray (#18779) 2025-06-02 21:15:13 -07:00
Nick Hill 2dbe8c0774 [Perf] API-server scaleout with many-to-many server-engine comms (#17546) 2025-05-30 08:17:00 -07:00
Will Eaton 64eaf5fe05 [P/D] NixlConnector DP fixes (#18903)
Signed-off-by: Will Eaton <weaton@redhat.com>
2025-05-29 18:08:40 +00:00
Nick HillandWill Eaton d1d61f3351 [BugFix] Make DP work with connector-delayed new requests (#18559)
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Will Eaton <weaton@redhat.com>
2025-05-29 18:04:18 +00:00
CYJiang d58f9c7f7a [Misc] Remove duplicate init for self.vllm_config (#18896)
Signed-off-by: googs1025 <googs1025@gmail.com>
2025-05-29 17:26:07 +00:00
Sanger Steel c32e249a23 [Frontend] [Core] Add Tensorizer support for V1, LoRA adapter serialization and deserialization (#17926)
Signed-off-by: Sanger Steel <sangersteel@gmail.com>
2025-05-22 18:44:18 -07:00
Nick Hillandkourosh hakhamaneshi cf5984b2fe [BugFix][DP] Send DP wave completion only from dp_rank==0 (#18502)
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: kourosh hakhamaneshi <kourosh@anyscale.com>
2025-05-21 20:25:25 -07:00
Yong Hoon Shin 907f935de9 [V1] Fix general plugins not loaded in engine for multiproc (#18326)
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
2025-05-21 01:21:49 -07:00
Nick Hill 59dd311cf5 [KVConnector] Keep KVTransferParams as a dict (#18033) 2025-05-14 08:05:57 -07:00
Nick Hill 55aa7af994 [V1] DP scale-out (2/N): Decouple engine process management and comms (#15977)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-05-13 10:48:21 -07:00
Cyrus Leung b922c2ebd2 [Bugfix] Fix entrypoints metrics tests (#18063)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-13 06:42:43 -07:00
Cyrus Leung 61e0a506a3 [Bugfix] Avoid repeatedly creating dummy data during engine startup (#17935)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-12 22:40:19 -07:00
Jade Zheng 289199feb6 [Core] Use platform-agnostic device control for DP engine core (#17245)
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
2025-05-12 12:09:16 -07:00
d19110204c [P/D] NIXL Integration (#17751)
Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Brent Salisbury <bsalisbu@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Brent Salisbury <bsalisbu@redhat.com>
2025-05-12 09:46:16 -07:00
Wallas Henrique d43f914d42 [Core][Feature] Input metadata dump on crash (#13407)
Signed-off-by: Wallas Santos <wallashss@ibm.com>
2025-05-07 22:15:09 +00:00
AlecandMark McLoughlin 0be6d05b5e [V1][Metrics] add support for kv event publishing (#16750)
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
2025-04-30 07:44:45 -07:00
rongfu.leng d803786731 [V1][Bugfix]: vllm v1 verison metric num_gpu_blocks is None (#15755)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
2025-04-30 18:20:39 +08:00
Nick Hill b07bf83c7d [BugFix] Avoid race conditions in zero-copy tensor transmission (#17203)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-04-26 06:00:07 +00:00
Shanshan Shen b724afe343 [V1][Structured Output] Clear xgrammar compiler object when engine core shut down to avoid nanobind leaked warning (#16954)
Signed-off-by: shen-shanshan <467638484@qq.com>
2025-04-24 06:15:03 -07:00
Rui Qiao c0dfd97519 [V1][PP] Optimization: continue scheduling prefill chunks (#17080)
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2025-04-24 05:27:08 -07:00
Nick Hill b2f195c429 [V1] Avoid socket errors during shutdown when requests are in in-flight (#16807)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-04-23 12:36:29 +08:00
Nick Hill 1e013fa388 [V1][DP] More robust DP/EP dummy request coordination (#16277)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-04-22 19:12:15 -07:00
Yihua Chengrshaw@neuralmagic.com <robertgshaw2@gmail.com>Robert ShawRémi DelacourtTyler Michael Smith
3408e47159 [P/D][V1] KV Connector API V1 (#15960)
Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: remi <remi@mistral.ai>
Co-authored-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Rémi Delacourt <54138269+Flechman@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
2025-04-17 13:22:40 -07:00