Commit Graph
3772 Commits
Author SHA1 Message Date
51d7c6a2b2 [Model] Support Mistral3 in the HF Transformers format (#15505)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-04-01 06:10:05 -07:00
8dd41d6bcc [Misc] Use envs.VLLM_USE_RAY_COMPILED_DAG_CHANNEL_TYPE (#15831)
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-01 06:07:53 -07:00
Isotr0py 0a298ea418 [Bugfix] Fix no video/image profiling edge case for MultiModalDataParser (#15828)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-04-01 18:17:11 +08:00
shangmingc 656fd72976 [Misc] Fix speculative config repr string (#15860)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-04-01 02:26:22 -07:00
Varun Sundar RabindranathandVarun Sundar Rabindranath 79455cf421 [Misc] Enable V1 LoRA by default (#15320)
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2025-04-01 16:53:56 +08:00
Wei Zeng 30d6a015e0 [Feature] specify model in config.yaml (#15798)
Signed-off-by: weizeng <weizeng@roblox.com>
2025-04-01 01:20:06 -07:00
Chen Zhang 3a5f0afcd2 [V1] Implement sliding window attention in kv_cache_manager (#14097)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-04-01 00:33:17 -07:00
Gregory Shtrasberg c7e63aa4d8 [ROCm] Use device name in the warning (#15838)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2025-04-01 00:10:48 -07:00
Lionel Villard 4a9ce1784c [sleep mode] clear pytorch cache after sleep (#15248)
Signed-off-by: <villard@us.ibm.com>
2025-03-31 22:58:58 -07:00
Alexander Matveev 7e4e709b43 [V1] TPU - Fix fused MOE (#15834)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
2025-03-31 22:58:07 -07:00
Alexey Kiryushin 63d8eabed0 [Bugfix]: Fix is_embedding_layer condition in VocabParallelEmbedding (#15824)
Signed-off-by: alexwl <alexey.a.kiryushin@gmail.com>
2025-03-31 22:57:59 -07:00
Percy e830b01383 [Bugfix] Fix extra comma (#15851)
Signed-off-by: haochengxia <xhc_1007@163.com>
2025-03-31 22:57:28 -07:00
Yan Ma ff6473980d [Bugfix][Model] fix mllama multi-image (#14883)
Signed-off-by: yan ma <yan.ma@intel.com>
2025-03-31 22:53:37 -07:00
KinfeyandCyrus Leung a164aea35d [Frontend] Add Phi-4-mini function calling support (#14886)
Signed-off-by: Kinfey <kinfeylo@microsoft.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-03-31 22:50:05 -07:00
Harry Mellor a76f547e11 Rename fallback model and refactor supported models section (#15829)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-03-31 22:49:41 -07:00
Ilya Markovandilmarkov b7b7676d67 [Distributed] Add custom allreduce support for ROCM (#14125)
Signed-off-by: ilmarkov <imarkov@redhat.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
2025-03-31 22:49:12 -07:00
Harry Mellor e6e3c55ef2 Move dockerfiles into their own directory (#14549)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-03-31 13:47:32 -07:00
Mark McLoughlin f98a4920f9 [V1][Core] Remove unused speculative config from scheduler (#15818)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-03-31 19:15:21 +00:00
Harry Mellor d4bfc23ef0 Fix Transformers backend compatibility check (#15290)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-03-31 10:27:07 -07:00
Alexander Matveev 9a2160fa55 [V1] TPU CI - Add basic perf regression test (#15414)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
2025-03-31 13:25:20 -04:00
yihong 2de4118243 fix: change GB to GiB in logging close #14979 (#15807)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-03-31 10:00:50 -07:00
shangmingc 239b7befdd [V1][Spec Decode] Remove deprecated spec decode config params (#15466)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-03-31 09:19:35 -07:00
Cyrus Leung 09e974d483 [Bugfix] Check dimensions of multimodal embeddings in V1 (#15816)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-31 09:01:35 -07:00
Mrm 037bcd942c [Bugfix] Fix missing return value in load_weights method of adapters.py (#15542)
Signed-off-by: noc-turne <2270929247@qq.com>
2025-03-31 06:56:42 -07:00
Alex Brooks c2e7507ad4 [Bugfix] Fix Crashing When Loading Modules With Batchnorm Stats (#15813)
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2025-03-31 13:23:53 +00:00
Naveassaf 3aa2b6a637 [Model] Update support for NemotronNAS models (#15008)
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
2025-03-31 20:35:14 +08:00
youkaichao 555aa21905 [V1] Fully Transparent Implementation of CPU Offloading (#15354)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-03-31 20:22:34 +08:00
Charlie Fu e85829450d [Feature][ROCm]Enable fusion pass for torch.compile on ROCm (#15050)
Signed-off-by: charlifu <charlifu@amd.com>
2025-03-31 04:42:18 -07:00
Chengyang LIUandchengyang liu 18ed3132d2 [Misc] update the comments (#15780)
Signed-off-by: chengyang liu <lcy4869@gmail.com>
Co-authored-by: chengyang liu <lcy4869@gmail.com>
2025-03-30 19:39:56 -07:00
Woosuk Kwon 9b459eca88 [V1][Scheduler] Avoid calling _try_schedule_encoder_inputs for every request (#15778)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-30 14:10:42 -07:00
yihong 70fedd0f79 fix: Comments to English for better dev experience (#15768)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-03-30 10:47:57 -07:00
kYLe bb103b29bf [Bugfix] Added embed_is_patch mask for fuyu model (#15731)
Signed-off-by: Kyle Huang <kylhuang@nvidia.com>
2025-03-30 03:45:08 -07:00
Cyrus Leung 803d5c35f3 [V1] Override mm_counts for dummy data creation (#15703)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-30 03:20:42 -07:00
pansicheng 7fd8c0f85c fix test_phi3v (#15321)
Signed-off-by: pansicheng <sicheng.pan.chn@gmail.com>
2025-03-30 02:01:34 -07:00
Julien Denize 6909a76201 [Bugfix] Fix Mistral guided generation using xgrammar (#15704)
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
2025-03-29 20:20:19 -07:00
Isotr0pyandChen Zhang 3c0ff914ac [Bugfix] Fix Mllama interleaved images input support (#15564)
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
2025-03-29 18:11:15 +00:00
Woosuk Kwon 2bc4be4e32 [V1][Minor] Simplify rejection sampler's parse_output (#15741)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-29 09:25:17 -07:00
Roger Wang c67abd614f [V1] Support interleaved modality items (#15605)
Signed-off-by: Roger Wang <ywang@roblox.com>
2025-03-29 06:30:09 -07:00
shangmingc 6fa7cd3dbc [Feature][Disaggregated] Support XpYd disaggregated prefill with MooncakeStore (#12957)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-03-29 04:01:46 -07:00
wwl2755 94744ba41a [V1] [Feature] Collective RPC (#15444)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
2025-03-29 03:39:14 -07:00
TJian 4965ec42d2 [FEAT] [ROCm] Add AITER int8 scaled gemm kernel (#15433)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-03-29 03:33:56 -07:00
yarongmu-google 7c1f760024 [Kernel][TPU][ragged-paged-attn] vLLM code change for PR#8896 (#15659)
Signed-off-by: Yarong Mu <ymu@google.com>
2025-03-28 21:13:15 -07:00
Nicolò Lucchesi da461f3cbf [TPU][V1][Bugfix] Fix w8a8 recompiilation with GSM8K (#15714)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-03-28 21:13:06 -07:00
Jinzhen Lin 5b800f0932 [Bugfix] set VLLM_WORKER_MULTIPROC_METHOD=spawn for vllm.entrypoionts.openai.api_server (#15700)
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
2025-03-28 21:12:26 -07:00
Varun Sundar RabindranathandVarun Sundar Rabindranath 1286211f57 [Bugfix] LoRA V1: add and fix entrypoints tests (#15715)
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2025-03-28 21:10:41 -07:00
Nick Hill 6d531ad7b8 [Misc][V1] Misc code streamlining (#15723)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-03-28 20:59:47 -07:00
pengyuangeandjiacai.liu de1cb38769 [Model] Support Skywork-R1V (#15397)
Signed-off-by: jiacai.liu <932997367@qq.com>
Co-authored-by: jiacai.liu <932997367@qq.com>
2025-03-28 20:39:21 -07:00
daniel-salib f3f8d8fff4 implement prometheus fast-api-instrumentor for http service metrics (#15657) 2025-03-29 00:12:02 +00:00
Reid 26df46ee59 [Misc] cli auto show default value (#15582)
Signed-off-by: reidliu41 <reid201711@gmail.com>
2025-03-28 22:23:00 +00:00
Alexander Matveev c3f687ac22 [V1] TPU - Fix the chunked prompt bug (#15713)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
2025-03-28 20:19:04 +00:00