Commit Graph
79 Commits
Author SHA1 Message Date
Zhonghua Deng 8a4e5c5f3c [V1][P/D]Enhance Performance and code readability for P2pNcclConnector (#20906)
Signed-off-by: Abatom <abzhonghua@gmail.com>
2025-07-16 22:13:00 -07:00
Nick HillandDavid Ben-David 574ad60db9 [KVConnector] Always call connector clear_metadata() at end of step (#20756)
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: David Ben-David <sdavidbd@gmail.com>
2025-07-10 22:37:27 +01:00
Or Ozeri cc876d0f29 [KVConnector] Aggregate finished requests on the scheduler (#19555)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
2025-07-10 09:22:18 +01:00
cd587c93ef [BugFix]: Properly set engine_id when using multi connector (#19487)
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: leiyiming <leiyiming@kingsoft.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-07-09 20:32:44 +00:00
Nicolò Lucchesi 71d1d75b7a [PD][Nixl] Remote consumer READ timeout for clearing request blocks (#20139)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-07-08 08:56:40 +01:00
Jee Jee Li 1caca5a589 [Misc] Add SPDX-FileCopyrightText (#20428)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-07-04 07:40:42 +00:00
Nicolò Lucchesi 8d775dd30a [Misc] Fix Unable to detect current VLLM config. Defaulting to NHD kv cache layout warning (#20400)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-07-03 14:56:09 -07:00
Ning Xie 1dba2c4ebe [Misc] adjust for ipv6 for mookcacke url parse (#20107)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-07-03 20:27:17 +00:00
Woosuk Kwon 7f280d69c9 [Optimization] Cache sampled token ids in model runner (#20291)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-07-01 11:01:31 -07:00
Nicolò Lucchesi 650d5dbd04 [Misc] Minor refactor of NIXL background handshake (#20068)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-07-01 12:40:14 +01:00
Zhonghua Deng ded1fb635b [Bugfix][V1][P/D]Fix the issue of occasional garbled output for P2pNcclConnector (#20263)
Signed-off-by: Abatom <abzhonghua@gmail.com>
2025-06-30 16:45:14 -07:00
Woosuk Kwon 2863befce3 [Optimization] Use Shared CachedRequestData Instance Across All Requests (#20232)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-06-30 09:07:50 -07:00
Nicolò Lucchesi 2582683566 [PD] Skip tp_size exchange with rank0 (#19413)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-06-25 20:04:39 -07:00
Nick Hill 55c65ab495 [P/D] Avoid stranding blocks in P when aborted in D's waiting queue (#19223)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-06-25 15:19:44 -07:00
lkchenandNick Hill 91f7d9d0b6 [P/D] Asynchronously do _nixl_handshake (#19836)
Signed-off-by: Linkun Chen <github@lkchen.net>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-06-24 12:46:10 -07:00
lkchen d0132f025d [Misc] Add type alias ReqId and EngineId for better readability (#19880)
Signed-off-by: Linkun Chen <github@lkchen.net>
2025-06-23 12:57:57 -07:00
lkchen 1bcd15edc7 [BugFix][P/D] Fix for cases where _recving_transfers can be cleaned up when *all* transfer done (#19874)
Signed-off-by: Linkun Chen <github@lkchen.net>
2025-06-22 22:41:53 -07:00
Nicolò LucchesiandNick Hill 2ebff5b77c [P/D][NixlConnector] Support tp_size > num_kv_heads deployments (#19691)
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-06-22 22:41:50 -07:00
Zhonghua Deng eccdc8318c [V1][P/D] An native implementation of xPyD based on P2P NCCL (#18242)
Signed-off-by: Abatom <abzhonghua@gmail.com>
2025-06-18 06:32:36 +00:00
Jiayi Yao cda92307c1 [Misc] Update lmcache connector with the latest connector apis (#19441)
Signed-off-by: YaoJiayi <120040070@link.cuhk.edu.cn>
2025-06-17 19:57:54 +00:00
Nicolò Lucchesi 4c8f64faa7 [V1][Kernel] Flashinfer HND KV cache layout (#19280)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-06-17 09:09:22 -04:00
Nicolò Lucchesi 1129e2b1ab [V1][NixlConnector] Drop num_blocks check (#19532)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-06-12 12:36:14 +00:00
Nick Hill aad30bd306 [BugFix] Fix MultiConnector test after HMA changes (#19291)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-06-06 20:16:24 +00:00
Nick Hill 65c69444b1 [Docs] Improve V1 KVConnector interface documentation (#19172)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-06-06 16:22:45 +08:00
Nicolò Lucchesi 9ef9173cfa [P/D][NixlConnector] Enable FlashInfer backend (#19090) 2025-06-05 17:10:15 +00:00
Robert ShawandNick Hill c56ed8bb0e [Bugfix][Nixl] Fix full prefix cache hit bug (#18632)
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-06-05 02:07:32 +00:00
Nicolò Lucchesi b2fac67130 [P/D] Heterogeneous TP (#18833)
Signed-off-by: nicklucche <nlucches@redhat.com>
2025-06-04 23:25:34 +00:00
Nicolò LucchesiandRobert Shaw 5d96533e22 [Bugfix][P/D] Fix Prefix Cache Bug (#18411)
Signed-off-by: nicklucche <nlucches@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
2025-06-03 23:53:16 +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
Robert Shaw b9f61e1387 [Bugfix][Nixl] Fix DP Metadata Handshake (#19008)
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
2025-06-02 03:30:41 +00:00
ptarasiewiczNV 8bf507d766 [P/D] NixlConnector use cache device index for memory registration (#18969)
Signed-off-by: Piotr Tarasiewicz <ptarasiewicz@nvidia.com>
2025-05-31 11:19:18 -04:00
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
maobaolong c24b1572ac Minor fix about MooncakeStoreConnector (#18721)
Signed-off-by: baoloongmao <baoloongmao@tencent.com>
2025-05-27 08:02:28 +00:00
Ning Xie 4ceafb6299 [MISC] typo fix and clean import (#18664)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-05-24 07:52:09 -07:00
Cyrus Leung 273cb3b4d9 [Doc] Fix top-level API links/docs (#18621)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-23 09:46:56 -07:00
Chen Zhang 6550114c9c [v1] Redo "Support multiple KV cache groups in GPU model runner (#17945)" (#18593)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-05-23 09:39:47 -07:00
lkchen e44d8ce8c7 [Bugfix] Set KVTransferConfig.engine_id in post_init (#18576)
Signed-off-by: Linkun Chen <github@lkchen.net>
2025-05-23 02:54:42 +00:00
Mark McLoughlin bb0a311213 Revert "[v1] Support multiple KV cache groups in GPU model runner (#17945) (#18459)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-05-21 10:25:23 -07:00
Nicolò Lucchesi cd8dfc6dfc [Misc] MultiConnector._connectors type (#18423)
Signed-off-by: nicklucche <nlucches@redhat.com>
2025-05-20 22:48:43 -07:00
wwl2755 d06dd72ba9 [Bugfix][Failing Test] Fix nixl connector test when promt size < block size (#18429)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
2025-05-20 22:41:44 -07:00
Gregory Shtrasberg 0c15c2e486 [Bugfix] config.head_dim is now explicitly set to None (#18432)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2025-05-20 21:04:33 -07:00
Nick HillandNicolò Lucchesi 1b15df2546 [BugFix] Fix handling of num_computed_tokens with connector (#18232)
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
2025-05-19 09:03:25 -07:00
David Ben-DavidandDavid Ben-David 3e0d435027 [P/D][V1] Support dynamic loading of external KV connector implementations (#18142)
Signed-off-by: David Ben-David <davidb@pliops.com>
Co-authored-by: David Ben-David <davidb@pliops.com>
2025-05-17 06:40:39 +00:00
Michael Goin fd195b194e [V1][P/D] Local attention optimization for NIXL (#18170)
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-05-16 21:16:33 -04:00
Nick Hill 0ceaebf87b [BugFix] Fix ordering of KVConnector finished send/rcv sets (#18211)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-05-16 09:20:54 -07:00
Nick Hill 1db4f47f81 [BugFix] Fix multi async save in MultiConnector (#18246)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-05-16 08:13:47 -07:00
Russell Bryant a8f5aec20a [V1] Update zmq socket creation in nixl connector (#18148)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-05-14 23:17:57 -07:00
Chen Zhang e60f550b38 [v1] Support multiple KV cache groups in GPU model runner (#17945)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-05-14 18:54:54 -07:00
Michael GoinandNick Hill 2142035b51 [V1] Support multiple kv connectors (#17564)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-05-14 16:28:02 -07:00
Nick Hill 59dd311cf5 [KVConnector] Keep KVTransferParams as a dict (#18033) 2025-05-14 08:05:57 -07:00