6026 Commits

Author SHA1 Message Date
Russell Bryant
790b79750b
[Build/CI] Fix env var typo (#15305)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-03-21 22:28:46 +00:00
Nicolò Lucchesi
cfbb8c930f
[TPU][V1] MHA Pallas backend (#15288)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-03-21 08:50:39 -07:00
Cyrus Leung
baec0d4de9
Revert "[Feature] specify model in config.yaml (#14855)" (#15293)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-21 08:30:23 -07:00
Mengqing Cao
c21b99b912
[Bugfix][VLM] fix llava processor (#15285)
Signed-off-by: Mengqing Cao <cmq0113@163.com>
2025-03-21 05:14:36 -07:00
Chen Zhang
93a00d7dde
[v1] Refactor KVCacheConfig (#14079)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-03-21 04:56:27 -07:00
Russell Bryant
61e8c18350
[Misc] Add cProfile helpers (#15074)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-03-21 04:56:09 -07:00
Isotr0py
8afcd0f633
[Bugfix] Fix broken kernel test due to missing rename for v1 Triton backend (#15282)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-03-21 11:42:06 +00:00
Lehua Ding
91ca929dc7
[V1] Fix wrong import path of get_flash_attn_version (#15280)
Signed-off-by: Lehua Ding <lehuading@tencent.com>
2025-03-21 03:54:11 -07:00
Isotr0py
84e00adc8a
[Bugfix] Fix incorrect resolving order for transformers fallback (#15279)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-03-21 03:54:08 -07:00
Isotr0py
47c7126213
[Misc] Add attention mask pre-computation optimization back to Qwen2.5-VL (#15273)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-03-21 10:32:33 +00:00
Shanshan Shen
a989ca2bf6
[Bugfix] Add int8 torch dtype for KVCache (#15260)
Signed-off-by: shen-shanshan <467638484@qq.com>
2025-03-21 08:58:28 +00:00
Wei Zeng
0fa3970deb
[Feature] specify model in config.yaml (#14855)
Signed-off-by: weizeng <weizeng@roblox.com>
2025-03-21 00:26:03 -07:00
Nick Hill
da6ea29f7a
[V1] Avoid redundant input processing in n>1 case (#14985)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-03-20 22:24:10 -07:00
Edwin Hernandez
7297941b38
[Doc] Update LWS docs (#15163)
Signed-off-by: Edwinhr716 <Edandres249@gmail.com>
2025-03-20 21:18:47 -07:00
Isotr0py
f8a08cb90d
[V1] Enable Triton(ROCm) Attention backend for Nvidia GPUs (#14071)
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-21 03:14:19 +00:00
Siyuan Liu
b15fd2be2a
[Hardware][TPU] Add check for no additional graph compilation during runtime (#14710)
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
2025-03-21 03:05:28 +00:00
Woosuk Kwon
e588ac237c
Add an example for reproducibility (#15262)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-20 19:55:47 -07:00
Cody Yu
5df2da5b97
[Misc] Better RayExecutor and multiprocessing compatibility (#14705)
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
2025-03-20 19:27:46 -07:00
Woosuk Kwon
11b986b3fb
[Docs] Trim the latest news in README (#15261)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-20 19:24:21 -07:00
Chih-Chieh Yang
296f927f24
[Model] RE: Mamba2 Prefill Performance Tweaks: Fixing Flurry of Unnecessary Memory Copies (#14857)
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
2025-03-20 19:21:08 -07:00
Travis Johnson
0032903a5b
[Bugfix] detect alibi and revert to FA2 (#15231)
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2025-03-20 19:20:16 -07:00
Hyesoo Yang
47195057e9
[V1][TPU] Speed up top-k on TPU by using torch.topk (#15242)
Signed-off-by: Hyesoo Yang <hyeygit@gmail.com>
2025-03-20 19:19:40 -07:00
Harry Mellor
6edbfa924d
Mention extra_body as a way top pass vLLM only parameters using the OpenAI client (#15240)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-03-20 19:18:36 -07:00
Isotr0py
1e508343e1
[Bugfix] Fix incorrect qwen2.5-vl attention mask pre-computation (#15200)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-03-20 19:18:04 -07:00
Sage Moore
2e0b4cfde0
[ROCM] Upgrade torch to 2.6 (#15244)
Signed-off-by: Sage Moore <sage@neuralmagic.com>
2025-03-20 19:17:33 -07:00
Jee Jee Li
10f55fe6c5
[Misc] Clean up the BitsAndBytes arguments (#15140)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-03-20 19:17:12 -07:00
Lu Fang
d3ccbd6350
Fix CUDA kernel index data type in vllm/csrc/quantization/fused_kernels/layernorm_utils.cuh +10 (#15159)
Signed-off-by: Lu Fang <lufang@fb.com>
Co-authored-by: Richard Barnes <rbarnes@meta.com>
2025-03-21 10:01:11 +08:00
Varun Sundar Rabindranath
0cfe7d386d
[CI/Build] LoRA : make add_lora_test safer (#15181)
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2025-03-21 09:28:53 +08:00
Woosuk Kwon
0c6f5023c3
[V1] Scheduler Refactoring [1/N] - Add Scheduler Interface (#15250)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-03-20 17:50:43 -07:00
Yu Chin Fabian Lim
06dd08256f
Enforce that TP > 1 is not supported for Mamba2 if Quantization is Enabled. (#14617)
Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
2025-03-21 00:44:37 +00:00
Woosuk Kwon
2b22290ce0
[V1] Add flag to disable cascade attention (#15243)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-20 15:24:16 -07:00
Jason
d8e82bc06d
[Bugfix] fix V1 Engine crash while handling requests with duplicate request id (#15043)
Signed-off-by: Jiahui Sun <jhsun2020@gmail.com>
2025-03-20 10:01:02 -07:00
Chi Zhang
086b56824c
[ci] feat: make the test_torchrun_example run with tp=2, external_dp=2 (#15172)
Signed-off-by: Chi Zhang <zhangchi.usc1992@bytedance.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2025-03-21 00:30:04 +08:00
Harry Mellor
5a0905ba2a
Replace misc issues with link to forum (#15226)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-03-20 23:18:20 +08:00
Richard Liu
a8f12a63fd
Fix env vars for running Ray distributed backend on GKE (#15166)
Signed-off-by: Richard Liu <ricliu@google.com>
2025-03-20 14:59:33 +00:00
Harry Mellor
69ae2380c6
Add user forum to README (#15220)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-03-20 22:39:51 +08:00
Cyrus Leung
27261e40a6
[Bugfix] Multi-video inference on LLaVA-Onevision (#15082)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Isotr0py <2037008807@qq.com>
2025-03-20 14:10:45 +00:00
Quang-Linh LE
e3f813c33b
[macOS] Ugrade pytorch to 2.6.0 (#15129) 2025-03-20 01:22:40 -07:00
Wang Ran (汪然)
c607a2652b
Fixing Imprecise Type Annotations (#15192) 2025-03-20 01:19:55 -07:00
Kevin H. Luu
3d45e3d749
[release] Tag vllm-cpu with latest upon new version released (#15193) 2025-03-20 01:19:10 -07:00
billishyahao
742369d35a
[Frontend][Bugfix] support prefill decode disaggregation on deepseek (#14824)
Signed-off-by: billishyahao <bill.he@amd.com>
Co-authored-by: Zhai Feiyue <80079571+ZhaiFeiyue@users.noreply.github.com>
2025-03-20 00:00:33 -07:00
Wang Ran (汪然)
bfe2fe0af4
typo: Update config.py (#15189) 2025-03-19 23:31:21 -07:00
Matt Ritter
a8652f4f0f
Enable CUDA graph support for llama 3.2 vision (#14917)
Signed-off-by: Matt Ritter <100659061+mritterfigma@users.noreply.github.com>
2025-03-19 23:29:16 -07:00
Cyrus Leung
2f726b241e
[Doc] Update README.md (#15187)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-20 13:25:58 +08:00
Mickaël Seznec
a597a57595
[Attention] Flash Attention 3 - fp8 (#14570)
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
2025-03-20 01:14:20 -04:00
Chauncey
ae65f3e237
[Misc]fixed disable these http request logs (#14754)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-03-19 21:53:40 -07:00
Roger Wang
34868b106a
[Doc] Update Mistral Small 3.1/Pixtral example (#15184)
Signed-off-by: Roger Wang <ywang@roblox.com>
2025-03-20 04:46:06 +00:00
Russell Bryant
1f16b7fe74
[Core][V0] Add guidance backend for structured output (#14589)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Loc Huynh <lohuynh@microsoft.com>
Co-authored-by: Michal Moskal <michal@moskal.me>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
2025-03-19 21:33:51 -07:00
Jennifer Zhao
b88be22165
[Benchmark] Allow oversample request in benchmark dataset (#15170)
Signed-off-by: Jennifer Zhao <ai.jenniferzhao@gmail.com>
2025-03-20 12:32:58 +08:00
Nicolò Lucchesi
d8c6d7d6b5
[V1][TPU] Support V1 Sampler for ragged attention (#14227)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-03-19 21:00:39 -07:00