Commit Graph
22230 Commits
Author SHA1 Message Date
apex-mochen c4fa6f36a7 [Tests][Multimodal] Cover scoped processor kwargs precedence (#59399)
Signed-off-by: apex-mochen <2756823972@qq.com>
2026-09-30 10:54:32 +00:00
0103a9b96f [Quantization] Add per-token NVFP4 CuTe-DSL MoE backend (#50030)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: S1ro1 <matej.sirovatka@gmail.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
2026-09-30 10:42:03 +00:00
d5ee309314 [UX] Tag torch.compile log lines with the component being compiled (#48133)
Signed-off-by: Francesco Fusco <ffu@zurich.ibm.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
2026-09-30 10:34:31 +00:00
Akash kaothalkarAkash kaothalkarAntigravityLi, Jiang <jiang1.li@intel.com>
d71f662606 [Bugfix][Model][CPU] Fix Mamba2 quantized in_proj weight and scale loading for TP >1 (#58083)
Signed-off-by: Akash kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Akash kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Antigravity <antigravity@google.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
2026-09-30 17:59:02 +08:00
Mathew Oddenandopencode+glm-5.3+vllm 91dab0eb7f [ROCm][Perf] Allocate the pinned PLE prefetch buffer lazily (#58797)
Signed-off-by: Mathew Odden <modden@redhat.com>
Co-authored-by: opencode+glm-5.3+vllm <opencode+glm-5.3+vllm@example.com>
2026-09-30 17:43:16 +08:00
djramicandAndreas Karatzas 50319916a3 [ROCm][CI] Move Basic Models (Other) to MI355 (#59400)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-30 09:42:25 +00:00
yhcheong (vllmellm) 16d4ac4ba3 [ROCm][MoE] Support MiMo-V2.6 MXFP4 on gfx942 (#58262)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
2026-09-30 17:23:00 +08:00
aoshen02andClaude Opus 5.5 749192ff41 [CI] Skip the IPC weight-checker test on non-CUDA platforms (#59398)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 09:20:32 +00:00
713ec07655 [Frontend][RL] Track HTTP weight operation outcomes and concurrency (#55781)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
2026-09-30 09:19:43 +00:00
Akash kaothalkarAkash kaothalkarAntigravityLi, Jiang <jiang1.li@intel.com>
ae66f9a97c [Hardware][PowerPC] Prioritize bfloat16 for auto dtype on PowerPC (#58528)
Signed-off-by: Akash kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Akash kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Antigravity <antigravity@google.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
2026-09-30 17:14:17 +08:00
Avishek GoswamiandAvishek Goswami fb91712b38 [Model] Make the BERT/RoBERTa embedding class a class attribute (#59348)
Signed-off-by: Avishek Goswami <avishek.goswami@ibm.com>
Signed-off-by: Avishek Goswami <86944690+GOavi101@users.noreply.github.com>
Co-authored-by: Avishek Goswami <avishek.goswami@ibm.com>
2026-09-30 08:57:21 +00:00
Simon Danielsson 3627a6a124 [ROCm][Perf][GLM-5.3-Flash] Stride-aware decode KDA (#57979)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
2026-09-30 08:16:29 +00:00
Alexandra Sidorova b81984879a [K2 Horizon] fold partial-RoPE permutation into q/k (and norm) weights (#55335)
Signed-off-by: Alexandra Sidorova <asidorov@amd.com>
2026-09-30 16:03:37 +08:00
cjackal 0a30bc3f9a [Model] Extend device-side mm normalization to GLM4V/GLM5Next (#55389)
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
2026-09-30 15:44:46 +08:00
Zheng Gong 8ee4069033 [ROCm][DSv4.1][Perf] Use the shared prefill chunk plan in the ROCm sparse prefill (#58539)
Signed-off-by: Zheng Gong <zgong@amd.com>
2026-09-30 15:31:51 +08:00
Bugen ZhaoandClaude Opus 5.5 87228cff01 [Rust Frontend] Replay roundtrip output grammars through XGrammar (#59143)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 07:29:01 +00:00
Zheng GongandCursor fcd317cf33 [ROCm][DSv4][Perf] Use the shared prefill chunk plan in the ROCm sparse prefill (#58405)
Signed-off-by: Zheng Gong <zgong@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-30 15:26:57 +08:00
Rehan KhanandLi, Jiang <jiang1.li@intel.com> 583637f126 [CPU][Perf] Add vectorized Sampler Kernel (#53913)
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
2026-09-30 15:16:28 +08:00
Fangzhou AiandCursor Agent 77e8b02c8d [ROCm][Perf] Add opt-in a4w4 (FP4 activation) MoE for DeepSeek V4.1 on AITER (#58819)
Signed-off-by: fai <fangzhouai@gmail.com>
Signed-off-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
Co-authored-by: Cursor Agent (Claude Sonnet 5) <cursoragent@cursor.com>
2026-09-30 15:07:44 +08:00
e5f3d08d72 [Frontend][RL] Align sleep-mode API responses and operation metrics (#52864)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-29 23:16:38 -07:00
Ning Xie 29773c722b [Observability] log sub process killing in process manager force kill (#52314)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2026-09-30 06:13:24 +00:00
Andreas Karatzas 866fa130fa [Core] Bound UniProc EngineCore startup threads to available CPUs (#58946)
Signed-off-by: Andreas Karatzas <andreas.karatzas@protonmail.com>
2026-09-29 23:02:55 -07:00
Harshal AdhavCursorLi, Jiang <jiang1.li@intel.com>
5faf81a429 [CPU][Whisper] Support W4A16 quantized Whisper on the CPU WNA16 kernel (#58268)
Signed-off-by: Harshal Adhav <harshal.adhav@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
2026-09-30 13:52:53 +08:00
Ting SUNandFlora Feng fcf4750466 [Bugfix][Frontend] Constrain forced named tool choice with empty parameters to a JSON object (#45290)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
2026-09-30 05:44:35 +00:00
liuzhenwei 6945d142e5 [XPU] Use encoder-only model runner for EC producer instances (#59320)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
2026-09-30 13:43:21 +08:00
Fabian Joswigandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 1117140edb [Bugfix][Model] Fix DiffusionGemma silently freezing attention mask under CUDA graph replay (#51994)
Signed-off-by: Fabian Joswig <fjosw@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-30 05:34:26 +00:00
Ting SUNandFlora Feng 329e6eee3f [Bugfix][Frontend] Report named Anthropic tool calls as tool_use (#47598)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
2026-09-30 05:32:38 +00:00
Shijie Lyu ac68c30872 [Bugfix][Frontend] Ignore reused prompt token ids for media in /v1/responses (#59173)
Signed-off-by: Shijie Lyu <lshjhf@gmail.com>
2026-09-30 05:21:09 +00:00
Flora FengandClaude Fable 5.1 a3af78384a [Agents] Add API compatibility checking skill (#58003)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-30 04:59:48 +00:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 834ad456d3 [Refactor] Remove dead tests code (#58916)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-30 04:39:03 +00:00
90e13fc757 [Bugfix][HiSparse] Never allocate GPU pages without host backing (#59036)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 04:13:29 +00:00
Mia Ojeda e006d761a5 [Bugfix][CPU][DiffusionGemma] Support narrower canvas w/ sync scheduling (#59107)
Signed-off-by: ojeda-e <estefania.b.ojeda@gmail.com>
2026-09-29 23:28:50 -04:00
Louie Tsai 1b77cc3d67 [Benchmark] Add sweep warmup and failure recovery (#57305)
Signed-off-by: louie-tsai <louie.tsai@intel.com>
2026-09-30 11:16:41 +08:00
42d9f8ccdb support rl feature : weight checker (#51350)
Signed-off-by: shiyuan680 <yangcheng104@huawei.com>
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: shiyuan680 <yangcheng104@huawei.com>
Co-authored-by: Ronald1995 <ronaldautomobile@163.com>
Co-authored-by: DeepSeek Harness <noreply@deepseek.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
2026-09-30 03:13:43 +00:00
a8e069f81b [Bugfix][MiniMax M3] Share target embeddings with MTP under PP (#58648)
Signed-off-by: Peiyuan Zhou <peiyuanzhou1994@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2026-09-29 20:04:10 -07:00
Matthew BonanniandClaude Opus 5.5 2798f66860 [Bugfix][HiSparse] Resolve MTP verification rows with a union residency kernel (#59235)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 03:01:45 +00:00
Kevin H. LuuandCodex bec710fccf [CI] Fix mock type narrowing in LoRA serving test (#59344)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-29 19:55:04 -07:00
Wei Zhao 678baf5372 [Dependency] Upgrade FlashInfer to 0.7.0.post1 (#59323)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
2026-09-30 02:34:36 +00:00
Bugen ZhaoandClaude Sonnet 5.5 8039d3cbfd [Rust Frontend] Use the MiMo structural-tag builder (#59148)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-09-30 01:34:46 +00:00
Nick HillandClaude Opus 5.5 105a4e097b [Bugfix][Frontend] Reject LoRA adapters named after a served model (#59286)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-29 18:29:38 -07:00
765872e7ed [Core][BugFix] Tag prefix-cache extra keys by source (#51899)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Lucas Bourtoule <35483370+dhalf@users.noreply.github.com>
Co-authored-by: Tai An <antai12232931@outlook.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-29 18:24:59 -07:00
xiangdongandKunshang Ji 09c47db1ca [XPU][CI]Skip test_abort_timeout_on_prefiller in nightly (#58307)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-09-29 17:29:59 -07:00
Flora Feng 7ca31ef599 [Bugfix][Responses API] Build streamed final response from streamed items (#59307)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-09-30 00:16:05 +00:00
Lio Einaudiandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 4e0a414c44 [Kernel][Perf] Add TP=2/4/8 per-rank shapes to the sm_120 batch-invariant matmul table (#58495)
Signed-off-by: LioEinaudi <zhao3024667639@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-29 23:51:50 +00:00
Harshilandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> be255076d0 [Bugfix] Reject a prefix_match_unit that a single KV cache group cannot honor (#58021)
Signed-off-by: QHarshil <harshil_c@hotmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-29 23:12:15 +00:00
Juan Pérez de AlgabaandCursor eec2a86b1e [Security] Bump nltk, aiohttp, pillow, and datamodel-code-generator (#59249)
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-29 16:00:36 -07:00
RongJie GandFlora Feng 0755e69e75 [Bugfix][Responses API] Preserve built-in tool output call IDs (#55596)
Signed-off-by: CorgiBoyG <111257566+CorgiBoyG@users.noreply.github.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
2026-09-29 22:45:14 +00:00
c37f86e572 [Bugfix] GLM-5.3-Flash: fp8 plan dtype on SM90 sparse MLA, and right-size the indexer prefill workspace (#55222)
Signed-off-by: Mikhail Kostryukov <mike@triptrack.net>
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: Mikhail Kostryukov <drakosha81@proton.me>
Co-authored-by: NickLucche <nicolo.lucchesi@mistral.ai>
2026-09-29 22:36:39 +00:00
Tyler Michael SmithandCodex 50239dfc4d [WideEP] Change DeepEPv2 to auto select hybrid mode by default (#57991)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-29 18:36:30 -04:00
Flora Feng 797505747f [Bugfix][Frontend] Honor parallel_tool_calls=false in the Responses API (#59298)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-09-29 22:36:11 +00:00