Commit Graph
18547 Commits
Author SHA1 Message Date
Nicolò LucchesiandGitHub d79855eaac [Docs] kv_sharing_fast_prefill correction (#47044)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
2026-07-08 01:17:46 -07:00
51e5372f3d [Model][HunyuanVL] Use native transformers processor and adapt to transformers 5.13 (#47872)
Co-authored-by: manayang <manayang@tencent.com>
2026-07-08 07:58:23 +00:00
Ace EldeibandGitHub 7cc2e8e74f fix: hash speculative draft model config (#47911)
Signed-off-by: Ace Eldeib <aeldeib@coreweave.com>
Signed-off-by: Ace Eldeib <alexeldeib@gmail.com>
2026-07-08 08:36:30 +01:00
Hongxia YangandGitHub 2c64b4c1cc [ROCm] fixed aiter master flag and expert parallelism compatibility on minimax-m3-mxfp8 (#47158)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
2026-07-08 15:26:17 +08:00
d35eba302f [Bugfix] Avoid leaking Pydantic repr in tool_choice error message (#47028)
Signed-off-by: muhammadfawaz1 <135441198+muhammadfawaz1@users.noreply.github.com>
Co-authored-by: Mahad Durrani <114791389+mahadrehmann@users.noreply.github.com>
2026-07-08 15:00:59 +08:00
Nicklas FrahmandGitHub c0e8e1f12a [Bugfix] Register VLLM_BUILD_* and VLLM_IMAGE_TAG provenance env vars (#45313)
Signed-off-by: Nicklas Frahm <nicklas.frahm@gmail.com>
2026-07-08 06:21:12 +00:00
Zach ZhuandGitHub 5d5fab0061 [Bugfix][Frontend] Fix http_requests_total metric recording some 4xx errors as 5xx (#44303)
Signed-off-by: Zach Zhu <zzqshu@126.com>
2026-07-08 05:33:21 +00:00
2afa3f7e95 [Perf] Minimax M3 - Support cross-layer allreduce-norm fusion (#47631)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
2026-07-07 21:16:32 -07:00
80eb01e93d [Bugfix] DSV4 TP16 garbage output (#47493)
Signed-off-by: Jeff Ma <jeffjma@umich.edu>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2026-07-07 21:04:33 -07:00
d9e57ea82e [ROCm][Perf] MXFP8 dense-linear + grouped-MoE GEMM optimizations for MiniMax-M3 (#46117)
Signed-off-by: amd-ethany <amd-ethany@users.noreply.github.com>
Co-authored-by: amd-ethany <amd-ethany@users.noreply.github.com>
2026-07-08 04:03:34 +00:00
9021589498 [Minimax-M3] Using tok_sparse_select from MSA instead of triton kernels (#47502)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-07 21:01:12 -07:00
Ting SUNandGitHub 0303f37a54 [Bugfix][Pooling] Align CrossEncoder token type ids after truncation (#47772)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
2026-07-08 03:59:22 +00:00
Walter Beller-MoralesandGitHub dd127d82ed [Core][Engine] only materialize tokens when thinking budget is in req (#47053)
Signed-off-by: walterbm <walter.beller.morales@gmail.com>
2026-07-07 21:02:38 -06:00
0ca6eee743 [Core] Pass request context to CPU offload cache policy touch (#47744)
Signed-off-by: jacklin78911-collab <jacklin78911@gmail.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-07-08 05:56:25 +03:00
Isotr0pyandGitHub 5e975eae1a [Bugfix] Avoid blocking model launching when no system ffmpeg available for TorchCodec (#47888)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
2026-07-08 10:52:25 +08:00
Martin HickeyandGitHub f7fc0ca993 [Frontend] Add endpoint plugins framework (#47454)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
2026-07-08 10:00:41 +08:00
Rahul VishwakarmaandGitHub f7efab58ec [CPU][Bugfix] Fix flaky ShortConv prefill test on ARM (uninitialized weights) (#47848)
Signed-off-by: Rahul Vishwakarma <Rahul.Vishwakarma2@ibm.com>
2026-07-07 18:20:09 -07:00
Nils MattesonGitHubNils Mattesonmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
e97c3cb303 [Core] Persist and reuse the memory-profiling result across boots (opt-in) (#47388)
Signed-off-by: Nils Matteson <nils@thaw.sh>
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
Co-authored-by: Nils Matteson <nils@thaw.sh>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-08 00:53:02 +00:00
4aceabf8c1 [ROCm][Bugfix] Key sparse-MLA persistent metadata on per-request context lengths (#47766)
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-07 19:22:34 -05:00
stefankoncarevicandGitHub 6e35c5e5af [ROCm][CI] Minimize comment in RocmAttention q_scale check (#47731)
Signed-off-by: stefankoncarevic <stefan.koncarevic@amd.com>
2026-07-07 19:16:08 -05:00
aad0fb741b [CI/Build] Accept ready-run-all-tests label in pre-commit gate (#47897)
Signed-off-by: AmeenP <ameen@primeintellect.ai>
Co-authored-by: AmeenP <ameen@primeintellect.ai>
Co-authored-by: Claude <noreply@anthropic.com>
2026-07-07 23:18:59 +00:00
yzong-rhandGitHub 7d2ce5750e [Bugfix] Patch Hopper MXFP4 OOB scales reads leading to NaN (#47910)
Signed-off-by: Yifan Zong <yzong@redhat.com>
2026-07-07 22:51:22 +00:00
Juan Pérez de AlgabaandGitHub 675f4295cd fix(security): bound completion prompt list to prevent unbounded engine fan-out (#47845)
Signed-off-by: jperezde <jperezde@redhat.com>
2026-07-07 22:48:20 +00:00
Jason LiandGitHub d99adcebdc [BugFix] Fix ModelOpt quantization inference for fused siblings (#47445)
Signed-off-by: jasonlizhengjian <jasonlizhengjian@gmail.com>
2026-07-08 03:19:42 +05:00
c8c2f838e7 Add tuned selective_state_update config for AMD Instinct MI355 (#47767)
Signed-off-by: vanshbhatia-amd <210711135+vanshbhatia-amd@users.noreply.github.com>
Co-authored-by: vanshbhatia-amd <210711135+vanshbhatia-amd@users.noreply.github.com>
2026-07-07 22:19:08 +00:00
Nils MattesonGitHubNils Mattesonmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
dd0d74cd92 [Doc] Surface the --kv-cache-memory suggestion at INFO and document fast-startup knobs (#47374)
Signed-off-by: Nils Matteson <nils@thaw.sh>
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
Co-authored-by: Nils Matteson <nils@thaw.sh>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-07 15:05:07 -07:00
55da232db6 [Bugfix] Pad Mamba page size instead of scaling block_size in unify_kv_cache_spec_page_size (#45207)
Signed-off-by: Sahil170595 <147995121+Sahil170595@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-07 22:01:34 +00:00
Wentao YeandGitHub 3f99883d97 [CI Bug Fix] Temp fix for v3.2 accuracy (#47902) 2026-07-07 16:36:03 -04:00
Nick CaoandGitHub 47c40bfe8a [Doc] Fix manylinux tag in installation guide (#47913)
Signed-off-by: Nick Cao <ncao@redhat.com>
2026-07-07 20:34:05 +00:00
3dd910da42 [Bugfix] Allow non-contiguous query in FlashInfer FP8 query quantization (#47908)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-07 20:11:34 +00:00
Benjamin ChislettandGitHub 7bd154375d [Bugfix] Fix mamba+dflash for MRV2 (#47698) 2026-07-07 15:59:13 -04:00
Rishabh SainiandGitHub 2f3f441f84 fix: include topic frame in KV events replay response (#45177)
Signed-off-by: RishabhSaini <rishabhsaini01@gmail.com>
2026-07-07 14:48:23 -04:00
d6875196ad [Bugfix] Exclude kv_cache_memory_bytes from CacheConfig.compute_hash (#47356)
Signed-off-by: Nils Matteson <nils@thaw.sh>
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
Co-authored-by: Nils Matteson <nils@thaw.sh>
2026-07-07 10:46:51 -07:00
Sting LinandGitHub abe41f28de Upgrade tpu-inference to v0.24.0 (#47835)
Signed-off-by: StingLin <sting.lin@cienet.com>
2026-07-07 17:15:32 +00:00
Roberto L. CastroandGitHub c3284c31f5 [Perf][3/N] Expand Triton kernel warmup coverage, Qwen (#47546)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
2026-07-07 17:06:59 +00:00
RobinandGitHub c74e751824 [Doc] Fix grammatically incorrect error message in gpu_worker and xpu_worker (#36715)
Signed-off-by: Hongbin10 <jdmjdm1998@163.com>
2026-07-07 17:03:06 +00:00
liuzhenweiandGitHub b93cbd7416 [XPU] Fix topk_sigmoid arg mismatch on XPU (#47858)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
2026-07-07 16:53:18 +00:00
Wentao YeGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
bdc6f3bfa1 [Bug] Fix tmp directory for lm_eval (#47755)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-07 16:40:12 +00:00
Ameen PatelGitHubClaudemergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
392d1b4d2e [BugFix][LoRA] Refresh punica metadata when LoRA slots are reassigned under an unchanged mapping (#47725)
Signed-off-by: AmeenP <ameenp360@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-07 08:53:55 -07:00
21b396abe1 AGENTS MD: Add suggestion on how to incorporate tests (#47784)
Signed-off-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
2026-07-07 08:16:08 -07:00
liuzhenweiandGitHub bdaf27519f [XPU] Fix Event init failure w/ blocking (#47868)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
2026-07-07 22:54:03 +08:00
Eldar KurtićandGitHub beb4327c46 Enable causal masking for SWA in vllm-project/speculators models (#47745)
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
2026-07-07 10:24:14 -04:00
c46ced1ee3 [kv_offload] Establish tier-owned KV event handling (#46544)
Signed-off-by: Change72 <changg@nvidia.com>
Signed-off-by: Chang Guo <changg@nvidia.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-07-07 16:55:20 +03:00
65dcde1695 [Bugfix] Fix PD disagg + MTP correctness for Qwen3.5(GDN) (#47466)
Signed-off-by: Dakai An <dakaian108@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-07-07 13:51:22 +00:00
65a7b46284 [KV-Offloading] Support workload identity for objectstore secondary tier (#47063)
Signed-off-by: Pierangelo Di Pilato <pierdipi@redhat.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-07-07 16:30:16 +03:00
Tyler Michael SmithGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Claude Opus 4.6
93e2ab7111 Disable dynamic speculative decoding when DP is enabled (#45963)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-07-07 12:52:41 +00:00
Lanze LiuandGitHub 8b745527cd [Bugfix] Fix UBatchWrapper CUDA graph key to sum all ubatches, not just first two (#43161)
Signed-off-by: Lanze Liu <lanzetech@gmail.com>
2026-07-07 12:42:31 +00:00
920469974a [UX] Log worker exit code when process dies unexpectedly (#38641)
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-07-07 12:36:29 +00:00
8b91cd5b20 [Bugfix][Core] Close underlying iterator in merge_async_iterators single-iterator fast path (#44726)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-07-07 05:13:41 -07:00
Harry MellorandGitHub dd94484577 Bump Transformers version to 5.10.4 (#41359)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-07-07 05:13:28 -07:00