[sync] vLLM 2026-07-12 — 766469a4c..83762b77b#1708
Merged
Conversation
…ck` #47912 (#48154) Upstream-vLLM: 766469a4c460043ae52cda19b1c52f0dc87e555c Co-authored-by: Micah Williamson <micah.williamson@amd.com>
Upstream-vLLM: cac3e70cd4f522eaab9d28323285d5e31238f907 Co-authored-by: ap9272 <ap9272@users.noreply.github.com>
Upstream-vLLM: f1a5adddb815610db46cae81f2a1d5a4609bf99d Co-authored-by: gnovack <novackgm@gmail.com>
Upstream-vLLM: feb384ada2a1da1981ccb713ea6bd3f90c44f7b4 Co-authored-by: Augusto Yao <augusto.yjh@antgroup.com>
…erving CUDA graph memory (#47366) Upstream-vLLM: 88e5e2c57be8ce6e25510c1249352a23b8a85ec4 Co-authored-by: peizhang56 <pei.zhang@amd.com>
…condary tiers (#47923) Upstream-vLLM: 2d814a00820daec7082599bea75ae1d0959a346c Co-authored-by: Chang Guo <changg@nvidia.com>
Upstream-vLLM: 95ed0feaa5cd7fb16d72c53ce04950aaf07c4698 Co-authored-by: Yan Xu <yancey.yx@alibaba-inc.com>
…port mode (#45261) Upstream-vLLM: e5588e49bc2642670116664a7fc4096e27adb179 Co-authored-by: GongLei-HW <1327185943@qq.com>
…ony models (#44301) Upstream-vLLM: 5715fde12c1e28eccd08a2394a114339b12a96c1 Co-authored-by: alberto <aperdomo@redhat.com>
Upstream-vLLM: 300e33797fac8a949a0ed89fab2633de96e65fa8 Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Upstream-vLLM: 074bdd0d9961fb7f81c9311e00c00cfd5aff77a3 Co-authored-by: Bugen Zhao <i@bugenzhao.com>
…Cosmos3-Super (#48211) Upstream-vLLM: 424df4f65df39a6e91f70e031e3c32b479501b25 Co-authored-by: Mingfei Guo <52491257+guoriyue@users.noreply.github.com>
…ightly) (#47180) Upstream-vLLM: f36284a8d21d3748df30c8f1b30357be711350b5 Co-authored-by: Andrey Talman <atalman@fb.com>
Upstream-vLLM: e23b19309b8705b21c3b3ff4129c9974ba15a419 Co-authored-by: ViranjanPagar <vpagar@nvidia.com>
…#47883) Upstream-vLLM: c241c7a2b015f8168d1c75e80cee15e45c18ba94 Co-authored-by: Reid <61492567+reidliu41@users.noreply.github.com>
Upstream-vLLM: 68ea76e78005bb53d9ef6b855b6c23411f5bb1e1 Co-authored-by: Isotr0py <Isotr0py@outlook.com>
…atch (#48113) Upstream-vLLM: 7614b88ebdd9739cd126daf6f33e867e27ce52a7 Co-authored-by: Nick Hill <nickhill123@gmail.com>
…(#48153) Upstream-vLLM: fabec87f63cdf0725d48e3eb6fdef9799837bcaf Co-authored-by: FAN YUCHEN <2994114386@qq.com>
…_ragged` (#48158) Upstream-vLLM: e257faf87d8e003451e8693262c2f90df4acea45 Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
…pere GPUs (#39988) Upstream-vLLM: b12cca6a2352ea6926864c925246eeb581be8caa Co-authored-by: XuZhou <17717803682@163.com>
…ity for… (#41811) Upstream-vLLM: 85c09e9885e346ea1612da30ebff5a75f67d2350 Co-authored-by: HuYiPeng <144002351+MynameFelix@users.noreply.github.com>
…well SM10x and SM110 (#48041) Upstream-vLLM: 978a6dfa3f79470e4459a454816202e78c1d2108 Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Upstream-vLLM: 08dfd68610d2e05a0d8ddc99c23488da6163df3f Co-authored-by: Michael Goin <mgoin64@gmail.com>
…MI350X / MI355X, gfx950) (#47419) Upstream-vLLM: c227aaa3f8edd02dae4583e27246430eebabfb25 Co-authored-by: larryli2-amd <Larry.Li@amd.com>
…lamp) (#48045) Upstream-vLLM: 735def4fcf39945b6e6c24769878760e3e113b15 Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Upstream-vLLM: f378f79b7c34d7ca94d53db34837929da2db03ed Co-authored-by: gnovack <novackgm@gmail.com>
Upstream-vLLM: 26ff616bbf43c5c5ecb847589705cebdbff46706 Co-authored-by: Nick Hill <nickhill123@gmail.com>
…</think> re-entry (#45984) Upstream-vLLM: ed908cf0a08af20839b82dc0638dae91b1ad630b Co-authored-by: Ashwin Giridharan <ashwing@users.noreply.github.com>
…m autotuning by default (#48268) Upstream-vLLM: 29fd6888922139e33980b81ec0c50477233eea00 Co-authored-by: Michael Goin <mgoin64@gmail.com>
…s for Marlin (#47851) Upstream-vLLM: 1bf3997eaeb41b1ef5cf25d87faa97b7f0be4788 Co-authored-by: Joe Rowell <joerowell4@gmail.com>
…E layers (#46276) Upstream-vLLM: 092387963c09ff3dde648e4ff620174d5d32c5d3 Co-authored-by: Jimmy Lee <58957694+thisisjimmyfb@users.noreply.github.com>
…47314) Upstream-vLLM: 9c18e90f6c94b90ecdaa99b2230389ba40e0fc69 Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Upstream-vLLM: 04d553f390fd37e09ab111936ef1592881299957 Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Upstream-vLLM: 3d99b0499aff7ce3b91942b0385558dab4eecf76 Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
…PI (#48269) Upstream-vLLM: bec0a4ede621bc9f1ec7be39b79ed2e286da4ca1 Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Upstream-vLLM: 4a6440acefbd4d977620bdb6dfb7fb325cd9bda7 Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Upstream-vLLM: 0b6636cbcbd3d40cb8c36459a3ff0f1f3c9b48a7 Co-authored-by: Qiming Zhang <qiming1.zhang@intel.com>
…ch (#48328) Upstream-vLLM: 1bd8f80a643efb5f977469692e458fd9a4fd3b4f Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Upstream-vLLM: 19069bcbd5be607a9c502e007951d8325d6a340e Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
…r (#48232) Upstream-vLLM: 76fedaa2a5382e4b76d236253da55b0646b1459c Co-authored-by: Yejing Lai <yejing.lai@intel.com>
…across attention backends (#44455) Upstream-vLLM: 51878e5b6e4cf27352c427b8508b4f338ba39c9c Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
…etch tasks on partial failure (#48333) Upstream-vLLM: 006731153693b01320feb93ab165de24fc364b0c Co-authored-by: ErenAta16 <erena6466@gmail.com>
…nnector (#43117) Upstream-vLLM: 54503ecec0f3ac31e5ecfc5f28652e4cc42307b5 Co-authored-by: Ievgen Bondarenko <ibondarenko@student.sierracollege.edu>
…ce (#47690) Upstream-vLLM: 9a48eef89a777fc7039d9765fb2f6fc618216948 Co-authored-by: Alejandro Paredes La Torre <99832715+AlejandroParedesLT@users.noreply.github.com>
…x incompatibilities (#48072) Upstream-vLLM: 8e981630c9336233ca9de91452f68918bddbc4e2 Co-authored-by: zhao, zhenhui <zhenhui.zhao@intel.com>
…(#46384) Upstream-vLLM: 481e481be786c1ca3229e26aa34c15ffd22375af Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Upstream-vLLM: fc1c548093029f6487bbdc9c612995dfe7621a75 Co-authored-by: vx120 <57470515+vx120@users.noreply.github.com>
Upstream-vLLM: a02984ed471488c0f0e8f73cab21be4325992d4c Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
…173) Upstream-vLLM: 83762b77b07e97c77f986e4bf5a9474952e47bb3 Co-authored-by: aoshen02 <aoshen@inferact.ai>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Automated upstream sync: 766469a4c460..83762b77b07e