Commit Graph

13284 Commits

Author SHA1 Message Date
Nicolò Lucchesi
d51e1f8b62 [Bugfix] Disable CG for Whisper+FA2 (#33164)
Signed-off-by: NickLucche <nlucches@redhat.com>
(cherry picked from commit 1f3a2c2944)
2026-01-28 02:16:41 -08:00
Roger Wang
5042815ab6 [Models] Kimi-K2.5 (#33131)
Signed-off-by: wanglinian <wanglinian@stu.pku.edu.cn>
Signed-off-by: wangln19 <96399074+wangln19@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: wanglinian <wanglinian@stu.pku.edu.cn>
Co-authored-by: wangln19 <96399074+wangln19@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
(cherry picked from commit b539f988e1)
2026-01-28 02:16:28 -08:00
Chauncey
afb390ab02 [CI] Fix AssertionError: MCP tool call not found in output_messages (#33093)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
(cherry picked from commit a2393ed496)
2026-01-28 02:16:14 -08:00
Robert Shaw
cf1167e50b [Bugfix] Fix Dtypes for Pynccl Wrapper (#33030)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
(cherry picked from commit 43a013c3a2)
v0.15.0rc0
2026-01-26 12:37:16 -08:00
Cyrus Leung
11b556878b [Refactor] Use data parser for matching data items to multi-modal UUIDs (#32955)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-26 15:00:28 +08:00
Danielle Robinson
ee484b3f4b Set splitk=1 for fused-moe-lora expand kernel (#32882)
Signed-off-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2026-01-25 22:52:34 -08:00
Woosuk Kwon
a9b53dd435 [Model Runner V2] Add LoRAState to consolidate lora logic (#33062)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-01-25 22:21:12 -08:00
Robert Shaw
254db42ede [Tests] Remove Duplicates (#33032)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
2026-01-26 05:23:54 +00:00
ltd0924
105d104576 [StepVL] support close img patch (#32923)
Signed-off-by: luotingdan <luotingdan@stepfun.com>
Signed-off-by: ltd0924 <32387785+ltd0924@users.noreply.github.com>
Co-authored-by: luotingdan <luotingdan@stepfun.com>
2026-01-25 20:56:39 -08:00
Lucas Wilkinson
566cdb6cfb [CI] Fix MHA attention test failure (AttributeError when model_config is None in ViT attention backend) (#33033)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-01-25 19:49:53 -08:00
Woosuk Kwon
2f0d3ba745 [Model Runner V2] Minor simplification for finish_requests (#33048)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-01-25 18:35:02 -08:00
Woosuk Kwon
edf927bc9f [Model Runner V2] Fix slot_mapping after #25954 (#33046)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
2026-01-25 18:29:49 -08:00
Andreas Karatzas
22aeb43007 [Bugfix][VLM] Fix transformers backend embed_multimodal for Qwen2.5-VL profiling (#32969)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-01-26 08:34:05 +08:00
Itay Etelis
a698e8e7ad [Model] Use mm_position to compute mrope positions for Qwen2.5-Omni (#32772)
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
2026-01-25 20:15:53 +08:00
zhanqiuhu
151e5451c2 [Doc] Add Qwen2.5 models to batch invariance tested models (#33016)
Signed-off-by: Zhanqiu Hu <zh338@cornell.edu>
2026-01-25 09:20:46 +00:00
Jee Jee Li
73b243463b [BugFix] Add env variable to control PDL in LoRA (#32836)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2026-01-25 16:32:30 +08:00
JJJYmmm
7e67df5570 [Bugfix] fix encoder cache hang in Qwen3VL (#32684)
Signed-off-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2026-01-25 05:17:31 +00:00
7. Sun
ff6c1da4e6 [Docs] Fix Apple silicon include path in CPU installation docs (#32977)
Signed-off-by: 7. Sun <jhao.sun@gmail.com>
2026-01-25 01:51:49 +00:00
Roberto L. Castro
fcb9df99bd [Perf][Kernel] Optimize FP4 quantization kernels (SM100F) (#32520)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
2026-01-24 18:45:27 -07:00
TJian
1ebdff412a [DOC] [ROCm] Update doc for v0.14.1 (#32998)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2026-01-25 09:13:21 +08:00
Joshua Deng
91601ff478 [Feature] add session based streaming input support to v1 (#28973)
Signed-off-by: Joshua Deng <joshuakdeng@gmail.com>
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-01-24 12:06:28 -08:00
yugong333
d4dbb7af63 Using max_loras + 1 to construct grid in fused_moe_lora (#32277)
Signed-off-by: Yu Gong <yu3.gong@gmail.com>
2026-01-24 12:39:30 -05:00
Maryam Tahhan
203d0bc0c2 [CPU] Improve CPU Docker build (#30953)
Signed-off-by: Maryam Tahhan <mtahhan@redhat.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
2026-01-24 17:08:24 +00:00
Fadi Arafeh
17ab54de81 [CPU Backend][BugFix] Fix failing Darwin pipelines (#33002)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
2026-01-24 17:02:22 +00:00
7. Sun
cd775bdbe0 [Tests] Replace flaky sleep with polling in test_background_cancel (#32986)
Signed-off-by: 7. Sun <jhao.sun@gmail.com>
2026-01-24 16:39:07 +00:00
Lucas Wilkinson
da5e7b12be [MLA] Fuse cat and qaunt for fp8 kv-cache (#32950)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-01-24 16:03:02 +00:00
Louie Tsai
719ac592ed Update CPU doc according to feedback (#32963)
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
Signed-off-by: Louie Tsai <louie.tsai@intel.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-24 16:02:44 +00:00
Hiroken.
1209b784f2 [Bugfix]: resolve torch.compile cache conflict between mm_encoder_tp_modes (#32842)
Signed-off-by: Hongjian Zhang <zhanghongjian@xiaohongshu.com>
Signed-off-by: Xingran Wang <wangxingran123456@outlook.com>
Co-authored-by: Xingran Wang <wangxingran123456@outlook.com>
2026-01-24 14:45:14 +00:00
Lukas Geiger
5fa0f6efa9 [EncoderCacheManager] Remove unnecessary copy (#32800)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2026-01-24 14:28:57 +00:00
david guan
bc0d291bfe feat: Complete LoRA support for MiniMaxM2 Fixes #32736 (#32763)
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-24 20:48:46 +08:00
Isotr0py
9ad7f89f55 [Models]: Make Multimodal config implicit in ViT implementation (#31972)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2026-01-24 20:34:26 +08:00
Hiroken.
6450b536a6 [Bugfix] Fix E2E latency calculation and add warmup support in mm_processor benchmark (#32646)
Signed-off-by: Hongjian Zhang <zhanghongjian@xiaohongshu.com>
Signed-off-by: Xingran Wang <wangxingran123456@outlook.com>
Signed-off-by: Hiroken. <105287758+HirokenOvo@users.noreply.github.com>
Co-authored-by: Xingran Wang <wangxingran123456@outlook.com>
2026-01-24 10:31:41 +00:00
7. Sun
0f19427db5 [Perf] Cache exc.errors() result in validation exception handler (#32984)
Signed-off-by: 7. Sun <jhao.sun@gmail.com>
2026-01-24 02:01:35 -08:00
Cyrus Leung
51931c5c9a [UX] Deduplicate sampling parameter startup logs (#32953)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-24 17:37:28 +08:00
Reagan Lee
06b557ecd9 feat(benchmark): add encoder forward pass benchmarking to mm-processor (#31655)
Signed-off-by: Reagan <reaganjlee@gmail.com>
Signed-off-by: Reagan Lee <96998476+reaganjlee@users.noreply.github.com>
Co-authored-by: Hiroken. <105287758+HirokenOvo@users.noreply.github.com>
2026-01-24 08:24:44 +00:00
Roger Wang
81c2a889ce [Doc] Ignore typo check on doc (#32999)
Signed-off-by: Roger Wang <hey@rogerw.io>
2026-01-23 23:52:22 -08:00
Isotr0py
8edaf38570 [Models] Add SharedFusedMoE support to Qwen3MoE (#32082)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2026-01-23 23:36:31 -08:00
Roy Wang
5c86a89805 [docs] Update governance process links (#32995)
Signed-off-by: esmeetu <jasonailu87@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
2026-01-23 23:32:44 -08:00
7. Sun
0ccecf8833 [Tests] Standardize RNG seed utility across test files (#32982)
Signed-off-by: 7. Sun <jhao.sun@gmail.com>
2026-01-24 06:47:14 +00:00
7. Sun
0b9a735e11 [Tests] Clarify pytest skip reasons with actionable context (#32981)
Signed-off-by: 7. Sun <jhao.sun@gmail.com>
2026-01-24 06:38:50 +00:00
7. Sun
14d03b8ddb [Perf] Cache xpu_get_mem_info() result to avoid duplicate calls (#32983)
Signed-off-by: 7. Sun <jhao.sun@gmail.com>
2026-01-23 20:56:23 -08:00
Michael Goin
d0cbac5827 [Dev UX] Add auto-detection for VLLM_PRECOMPILED_WHEEL_VARIANT during install (#32948)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Shengqi Chen <i@harrychen.xyz>
2026-01-23 19:15:17 -08:00
ruizcrp
c0d820457a Auth_token added in documentation as it is required (#32988)
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2026-01-24 03:03:05 +00:00
monajafi-amd
97ef11dd34 [ROCm][ViT] Enable Flash Attention Triton backend on RDNA3/RDNA4 (#32944)
Signed-off-by: mohammad najafi <mohammad.najafi@amd.com>
2026-01-24 10:03:07 +08:00
Xin Yang
ecc3dd66cc [Bugfix] Fix FusedMoE LoRA kernel offs_token out of bound value (#32279)
Signed-off-by: Xin Yang <xyangx@amazon.com>
2026-01-24 01:41:35 +00:00
Joe Runde
7e1f10d562 [Core][Bugfix] allow graceful worker termination (#32965)
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2026-01-23 17:28:45 -08:00
ElizaWszola
a28b94e6ef [Performance] Split FlashAttn attention and cache update (#25954)
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
2026-01-23 17:28:06 -08:00
dolpm
0118cdcc02 [fix] add VLLM_OBJECT_STORAGE_SHM_BUFFER_NAME to compile factors (#32912)
Signed-off-by: dolpm <34420038+dolpm@users.noreply.github.com>
2026-01-23 22:53:10 +00:00
Shengqi Chen
136c499f6e [CI] fix version comparsion and exclusion patterns in upload-release-wheels.sh (#32971)
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
2026-01-23 22:21:49 +00:00
joninco
ebd0a17e0e [Bugfix] Fix missing is_layer_skipped check for FusedMoE in AWQConfig (#32935)
Signed-off-by: jon <joninco@bullpoint.org>
2026-01-23 17:19:56 -05:00