[sync] vLLM 2026-07-15 — e26264f3e..647213129#1710
Merged
Conversation
…^2) (#39058) Upstream-vLLM: e26264f3ef5987a172162bbf497b8ae7ecbe0108 Co-authored-by: Tanish Malekar <60835372+tanish-malekar@users.noreply.github.com>
Upstream-vLLM: ee5a89f4d7b818af7d92770dbf6aa1b41b503b4a Co-authored-by: Tan Pin Siang <tanpinsiang@gmail.com>
Upstream-vLLM: 2595d5cebcc16d08a0f22b636e6e0741e4ea99b3 Co-authored-by: zzt <zengzetang.zzt@antgroup.com>
…8446) Upstream-vLLM: 775c1589ea9c7df49a866f900341e3645c5bd60c Co-authored-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
Upstream-vLLM: d973cce3ca809b44e0794ee044519e8ba91502e1 Co-authored-by: Rohan Potdar <rohan.potdar@amd.com>
… models on CPU (#46090) Upstream-vLLM: 05fa8183a6e2c1e1c6e4643d54b9709fa29ff753 Co-authored-by: guybd <guy.boudoukh@intel.com>
Upstream-vLLM: 8c5dafcd0986b75602e509c8d3bf7e59451b4181 Co-authored-by: Yejing Lai <yejing.lai@intel.com>
Upstream-vLLM: 9e57de7197f234f9d9187715d96e07e007048c0f Co-authored-by: Rehan Khan <Rehan.Khan7@ibm.com>
Upstream-vLLM: 36484e464a6cf763c5b4c8af7be8e19df324997a Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
Upstream-vLLM: b7b58d1eba73be5cceeb778212c02999e05c6f7c Co-authored-by: Andreas Karatzas <akaratza@amd.com>
…t fusion (#48064) Upstream-vLLM: 75fe92a3162a68d74581ec324f04684a752e3ad2 Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
…pability (#48011) Upstream-vLLM: bea70c7cfc10303f843cb4bda0e990e88f525f76 Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
…s into DeepseekV4 packing (#48256) Upstream-vLLM: 56a357ed33dec39357344816ccba2732109a96a8 Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
…pe (RFC #48305 §3.6) (#48390) Upstream-vLLM: 107a03ba63e005ff03424fed9c4e6cf551b98bb2 Co-authored-by: Karthik Kothuri <karthikkothuri2009@gmail.com>
Upstream-vLLM: 487dfb34185e12177ed9eb8f8b0fe337e85b591a Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Upstream-vLLM: b3cfca996c8340263cd1fb770a4c5e0b7f400b26 Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
…raph sizes (#48483) Upstream-vLLM: 1be6e937b2b49bae652370d80294f6171bd7b981 Co-authored-by: Omer Ullman Argov <118735753+omera-nv@users.noreply.github.com>
…467) Upstream-vLLM: c2c9f7c5e2445fc83137165c502326684bd98910 Co-authored-by: Yan Ma <yan.ma@intel.com>
… prefill cudagraph capture (#48261) Upstream-vLLM: 26587f9519e22a5c4549ead7595ad9ca3229c4fd Co-authored-by: Nick Hill <nickhill123@gmail.com>
Upstream-vLLM: 62286308c9e30adfef3780c6fbefeca5cf8f36ae Co-authored-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Upstream-vLLM: 43c8cbf79b75a583ef870b13e82dd33e68cf32b1 Co-authored-by: omerpaz95 <73347585+omerpaz95@users.noreply.github.com>
…eds (#48258) Upstream-vLLM: 9427c453863f3ab9e720748f04b9d6dd404ef602 Co-authored-by: stefankoncarevic <skoncare@amd.com>
Upstream-vLLM: 5c342876a6bde2689fa933548f31d0a9412a428a Co-authored-by: Gavin Morris <gmorriscs@gmail.com>
…soning → tool streaming boundary (#47606) Upstream-vLLM: 550218b13670fd6708916a645d8f538d773409c3 Co-authored-by: akii96 <aakif.nawaz@amd.com>
…g)` (#48513) Upstream-vLLM: 18c4067a5443ac04186e0936ace16268829ebe81 Co-authored-by: Micah Williamson <micah.williamson@amd.com>
Upstream-vLLM: 7fc97042c30eda7b45889162aaf64fa06d4055c4 Co-authored-by: Pavani Majety <pmajety@nvidia.com>
…cture (#47568) Upstream-vLLM: 7dc447dda7e6de38f3e1dcf63b0fc3e058a93e8e Co-authored-by: shanjiaz <zsjwpianpian@gmail.com>
…tention (#47782) Upstream-vLLM: 8ac8375270c1c86b0a8eaba7e738908a9a7303e1 Co-authored-by: Nick Hill <nickhill123@gmail.com>
Upstream-vLLM: 9a21f0d1a314b3ab160f0df913ab3552dae8771b Co-authored-by: wenpengw-nv <wenpengw@nvidia.com>
Upstream-vLLM: 7738ef35b8c62070773ef3cfd53f2a59d94626b1 Co-authored-by: Snehlata <sneh.lata@nutanix.com>
…45781) Upstream-vLLM: 50ac1c7bab47f14d56d86967532574824d02260e Co-authored-by: Artur Fierka <artur.fierka@intel.com>
…ing CVE remediation (#48583) Upstream-vLLM: 793cf79c89d4049124e756915468ac30318f2e50 Co-authored-by: Juan Pérez de Algaba <124347725+jperezdealgaba@users.noreply.github.com>
…xtVideo (#48594) Upstream-vLLM: b6754f536e9cb40a1e117705a44d74218873b437 Co-authored-by: karthik <56480632+gangula-karthik@users.noreply.github.com>
…ad (#47021) Upstream-vLLM: 7a74a9662bff4e5ef91f210f41b7f930de3df0bc Co-authored-by: tomerg-nvidia <tgilad@nvidia.com>
…e transfer width (#48411) Upstream-vLLM: 32aef4438822f90310d2a709b71192f30da2fea8 Co-authored-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
…tly in streaming and non-streaming (#48262) Upstream-vLLM: af453e5647773b6edb89230148b9fabeea0ace21 Co-authored-by: adhi29 <164859196+adhi29@users.noreply.github.com>
…e Parallel (#48036) Upstream-vLLM: 1ff9429655f01c804a7b17412144323e804f1324 Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
… config (#48520) Upstream-vLLM: b2f7d2560ae66122bb90b670d8c626216dc48f5f Co-authored-by: Michael Goin <mgoin64@gmail.com>
…437) Upstream-vLLM: ca3618bc698ed029c971a359f9b2b5bc1d041bb8 Co-authored-by: Daoyuan Li <94409450+DaoyuanLi2816@users.noreply.github.com>
…gauges (#47666) Upstream-vLLM: cdaa40d2a8c9297349669fc6e7db6dcb282df0b8 Co-authored-by: Srinivas Krovvidi <194645829+Srinivasoo7@users.noreply.github.com>
…he unified effective_batch grid (#48373) Upstream-vLLM: 7ffb98e248c03fc65c38472aac8ed2ee577c09a9 Co-authored-by: vanshbhatia-amd <vansh.bhatia@amd.com>
…peculative decoding (#46662) Upstream-vLLM: 32e632dfeb0860d11332754e641035ddd755f89f Co-authored-by: rishitdholakia13 <123388671+rishitdholakia13@users.noreply.github.com>
… (#48289) Upstream-vLLM: 0b54201a044c419e07a4bd464adf91e576640977 Co-authored-by: Michael Goin <mgoin64@gmail.com>
Upstream-vLLM: 05d4f8bba3aac85814c3fc42cfc60bef21bb2bb4 Co-authored-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
… (#48631) Upstream-vLLM: 313d01f507fc86306960aadf7939d2b7376b3a90 Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Upstream-vLLM: 9182e8697133e95f6e4ed236628a344b12e1c702 Co-authored-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
…8654) Upstream-vLLM: 0f0f28b537ac1a3d4bbeb74c706402d26dd27c76 Co-authored-by: Micah Williamson <micah.williamson@amd.com>
… (#48428) Upstream-vLLM: 7e950521b39fd201979a888eda82ff0f7ecc4731 Co-authored-by: Joe Rowell <joerowell4@gmail.com>
Upstream-vLLM: 3ca242d1b6282084b2a41e247810e632450c639a Co-authored-by: aoshen02 <aoshen@inferact.ai>
…wise reload (#44371) Upstream-vLLM: 0bd6b85a1f32cc3b32dc56d24ae8546897518ef3 Co-authored-by: Joan <94200647+joanvelja@users.noreply.github.com>
…T improvement. (#48137) Upstream-vLLM: 442c421e794317c37ab5e15feff1b05a035a5a18 Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Upstream-vLLM: f7aadae5e565c9a6cf85b8aa74280393fb8b6f28 Co-authored-by: gnovack <novackgm@gmail.com>
…ase (#47330) Upstream-vLLM: 6e073440b1753c6739c5e9a37b180e0d226a60bf Co-authored-by: Micah Williamson <micah.williamson@amd.com>
…h (#48525) Upstream-vLLM: 4f7fffb92f6e50fbbee47a89f6ebb4b662aba135 Co-authored-by: Karthik Kothuri <karthikkothuri2009@gmail.com>
…tensors (#46390) Upstream-vLLM: 9b2be4e9a55033a410a6f9e7c18eda5ce9105162 Co-authored-by: HDCharles <39544797+HDCharles@users.noreply.github.com>
Upstream-vLLM: fdf2cf66d3aa34800aaf1f4382fb2028886f0bae Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
…on (#44549) Upstream-vLLM: 96d2ceda4bb54d5601db7b464070860856c4f0b5 Co-authored-by: Russell Bryant <rbryant@redhat.com>
Upstream-vLLM: 37aa52821df831ea118ebfe3ec5b967227935733 Co-authored-by: Jane (Yuan) Xu <31798555+janeyx99@users.noreply.github.com>
…48379) Upstream-vLLM: 6472131298e7b9ce81651cac90cc2dcc28963b55 Co-authored-by: drakosha <mike@triptrack.net>
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: e26264f3ef59..6472131298e7