684 Commits

Author SHA1 Message Date
Jialin Ouyang
4228be7959
[Perf] Use np.ndarray instead of list[list[int]] to reduce GC overhead (#28245)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
2025-11-11 10:28:47 -08:00
Nicolò Lucchesi
a7ef3eb0cd
[NIXL] Generalize block-first backend layouts (FlashInfer-like) (#28282) 2025-11-11 16:57:43 +00:00
Matthew Bonanni
b30dfa03c5
[Attention] Refactor CUDA attention backend selection logic (#24794)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
2025-11-11 07:40:44 -05:00
Rémi Delacourt
6d54336ae5
[Bugfix] Fix llguidance backend, rollback when EOS was encountered (#25905)
Signed-off-by: Rémi Delacourt <remi@mistral.ai>
Signed-off-by: remi <remi@mistral.ai>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
2025-11-10 14:53:32 -05:00
Mark McLoughlin
6f7de33bed
[Metrics] Refactor LoRA state tracking (#26801)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-11-10 16:34:36 +08:00
usberkeley
4a8d6bd168
Fix cu_num_generated_tokens slicing logic in LogprobsLists.slice() method (#28214)
Signed-off-by: Bradley <bradley.b.pitt@gmail.com>
2025-11-09 19:11:46 +00:00
Nick Hill
289eb6c537
[Core] Simplify async KV output aggregation (#28327)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-11-09 09:44:13 -08:00
Nicolò Lucchesi
19d91ece4b
[CI] Fix flaky test_eagle_correctness test (#28364)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-11-09 16:04:59 +00:00
zhangsicheng5
2108a571d7
[DCP] Support dcp kv_cache interleave size > 1 (#26696)
Signed-off-by: zhangsicheng5 <zhangsicheng5@huawei.com>
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Signed-off-by: Qiu <qiuchunshuo@huawei.com>
Co-authored-by: QiuChunshuo <qiuchunshuo@huawei.com>
2025-11-09 04:45:27 +09:00
Andy Lo
47604137a2
[Bugfix] Spec decode + structured output + spec model max len edge case (#28298)
Signed-off-by: Andy Lo <andy@mistral.ai>
2025-11-08 19:44:25 +00:00
Harry Mellor
d9ab1ad9d1
reasoning_content -> reasoning (#27752)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-11-08 12:15:08 +00:00
Xiaohong (Sean) Chen
d0c7792004
[Bugfix][LoRA][Spec Decode] Support LoRA with speculative decoding (#21068)
Signed-off-by: Sean Chen <xiaohong_chen1991@hotmail.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Danielle Robinson <dcmaddix@gmail.com>
Co-authored-by: Haipeng Li <li2haipeng@gmail.com>
Co-authored-by: li2haipeng <44383182+li2haipeng@users.noreply.github.com>
2025-11-08 01:58:22 +00:00
Nick Hill
67a2da890e
[PerfFix] Avoid separate thread for MP executor shm spin (take 2) (#28319)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-11-07 22:11:03 +00:00
Nick Hill
da786e339e
[Core] Rework handling of async scheduling config (#28250)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-11-07 20:01:23 +00:00
Nicolò Lucchesi
68a72a5cc1
Revert "[PerfFix] Avoid separate thread for MP executor shm spin (#28012)" (#28289)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-11-07 15:07:01 +00:00
Matthew Bonanni
ca90f50304
[Test] Add non-MoE DP test coverage (#28235)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-11-06 20:59:57 +00:00
Chauncey
59a50afa08
[Frontend] OpenAI Responses API supports Tool/Function calling - non-harmony (#26874)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-11-06 10:40:03 +00:00
wangxiyuan
c3ee80a01a
[V0 deprecation]clean up is_v1_supported_oracle (#28116)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-11-06 16:05:32 +08:00
Zhewen Li
0b8e871e5e
[CI/Build] Fix test_defaults_with_usage_context in AMD CI (#27926)
Signed-off-by: zhewenli <zhewenli@meta.com>
2025-11-05 15:40:24 -08:00
Snehlata
e15601789b
[Feature]: Add corrupted request metric to V1 metrics system. (#27306)
Signed-off-by: atalhens <sneh.lata@nutanix.com>
2025-11-05 13:45:29 -08:00
Paul Zhang
faedbb4d4f
[Feature] Extend batch invariant torch.compile to B200 (#27856)
Signed-off-by: PaulZhang12 <paulzhan@fb.com>
2025-11-05 10:04:49 -08:00
Samuel Shen
40db194446
[CI]: Add LMCacheConnector Unit Tests (#27852)
Signed-off-by: Samuel Shen <slshen@uchciago.edu>
Co-authored-by: Samuel Shen <slshen@uchciago.edu>
Co-authored-by: Yihua Cheng <yihua98@uchicago.edu>
2025-11-05 09:45:57 -08:00
Isotr0py
3f5a4b6473
[Bugfix] Validate custom logits processor xargs for online serving (#27560)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-11-05 16:53:33 +00:00
Kuntai Du
86dca07d9b
[Hybrid allocator + kv connector] revert connector test changes related to hybrid allocator (#28011)
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
2025-11-05 10:36:31 +00:00
wangxiyuan
428bc7bf1c
[V0 deprecation] Remove VLLM_USE_V1 usage in most modules (#27955)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-11-04 20:51:16 -08:00
Nick Hill
938a81692e
[AsyncScheduling] Don't schedule past request max_tokens (#27922)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-11-04 17:06:28 +00:00
Nick Hill
c9f66da8fd
[PerfFix] Avoid separate thread for MP executor shm spin (#28012)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-11-04 08:33:55 -08:00
Mark McLoughlin
58279c60b5
[KV Connector] Make KVCacheConfig an explicit constructor argument (#27887)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-11-03 23:00:49 -08:00
Matthew Bonanni
01baefe674
Add TP parameter to attention tests (#27683)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-11-03 13:04:40 -08:00
Aurick Qiao
2c19d96777
[Spec Decode] Integrate Suffix Decoding from Arctic Inference (#25784)
Co-authored-by: Aurick Qiao <aurick.qiao@snowflake.com>
2025-11-03 09:23:31 -08:00
Lucas Wilkinson
4bc400f47e
[CI/Testing] Add basic single node dual batch overlap test (#27235)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-11-03 17:00:46 +00:00
Rémi Delacourt
cec7c28833
[Bugfix] Padded Eagle Specdec with Chunked Prefill (#26263)
Signed-off-by: Rémi Delacourt <remi@mistral.ai>
Signed-off-by: Rémi Delacourt <54138269+Flechman@users.noreply.github.com>
Signed-off-by: remi <remi@mistral.ai>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
2025-11-03 02:22:46 -05:00
Biswa Panda
1bf43ae35d
[BugFix][LoRA] use adapter_id instead of id field of lora_request (#27728)
Signed-off-by: Biswa Panda <biswa.panda@gmail.com>
2025-11-03 10:08:08 +08:00
Yihua Cheng
e675118849
[Add] cmdline argument parsing for KV cache offloading modules (#27621)
Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-11-01 07:17:07 +00:00
Nick Hill
0cdbe7b744
[Core] Async scheduling + structured outputs compatibility (#26866)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-11-01 00:35:04 +00:00
Chen Zhang
df334868ca
[Hybrid] A simpler algorithm to find kernel_block_size (#26476)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-10-31 21:30:28 +00:00
Matthew Bonanni
f29aeb5a25
Add FLASHINFER_MLA to test_mla_backends and add B200 CI run (#27663)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-10-31 11:12:19 -07:00
GuanLuo
d6517be3cd
[Bugfix] Missing NIXL metadata for handshake initialization if instance spans multi-node (#26338)
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
2025-10-31 10:16:00 -07:00
Zhewen Li
0fe0140408
[KV offload] Enable CPU KV offload on CUDA alike Platforms (#27770)
Signed-off-by: zhewenli <zhewenli@meta.com>
2025-10-30 22:10:29 +08:00
Lucas Wilkinson
b5d70751d8
[BugFix] Reordering extend logic fix (#27739)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-10-29 21:39:34 -07:00
Nick Hill
2ce5c5d3d6
[BugFix] Handle unscheduled requests properly when async scheduling (#27756)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-10-29 21:04:25 -07:00
Nicolò Lucchesi
0f95a1c3f2
[CI] Fix flaky test_two_responses_with_same_prev_id test (#27745)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-10-29 15:10:35 +00:00
Zhewen Li
9a0d2f0d92
[CI/Build] Skip cpu offloading test on AMD (#27690)
Signed-off-by: zhewenli <zhewenli@meta.com>
2025-10-29 12:55:51 +00:00
Dipika Sikka
413ef7a3b4
[Speculators] Move tests + fix integration (#27308)
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Rahul Tuli <rtuli@redhat.com>
Signed-off-by: rahul-tuli <rtuli@redhat.com>
Co-authored-by: Rahul Tuli <rtuli@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
2025-10-29 00:54:21 -07:00
Nick Hill
4fe5895361
[AsyncScheduling] Make async overlap work with logprobs (#27615)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-10-28 22:35:54 +00:00
Or Ozeri
111faf1118
[Core] Scheduler: Publish connector events after output (#25875)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
2025-10-28 21:01:33 +00:00
Wentao Ye
6afc28a9ba
[Test] Batch Invariant: Unit test using parameterized backend (#27478)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-28 13:51:35 -07:00
Lucas Wilkinson
141e6a0505
[Misc] Make reorder batch also separate extends (#27367)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-10-28 10:55:10 -07:00
Mohammad Miadh Angkad
a8c02fb5bf
[Bugfix][CI] Fix v1 attention backend tests and add CI coverage (#26597)
Signed-off-by: Mohammad Miadh Angkad <MAngkad.BSDSBA2027@aim.edu>
Signed-off-by: Mohammad Miadh Angkad <mangkad.bsdsba2027@aim.edu>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
2025-10-28 11:42:05 -04:00
Yeshwanth N
71b1c8b667
[Chore]:Extract math and argparse utilities to separate modules (#27188)
Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com>
Signed-off-by: Yeshwanth N <yeshsurya@gmail.com>
Signed-off-by: yeshsurya <yeshsurya@gmail.com>
2025-10-26 04:03:32 -07:00