Commit Graph
20845 Commits
Author SHA1 Message Date
omerpaz95andOr Ozeri 4b7f5ea1a0 [KV Connector] Allow metrics of multiple connectors of same types in multi connector. (#40010)
Signed-off-by: omerpaz95 <omerpaz95@gmail.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-04-19 07:49:10 +03:00
38907e4391 [Frontend] Preserve structured output special tokens in offline LLM.chat (#39352)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
2026-04-18 19:46:07 -04:00
d0359f3e04 [Bugfix] Guard mxfp4_experts_quant bindings on ENABLE_NVFP4_SM100 (#40191)
Signed-off-by: ultranationalism <www913363043@gmail.com>
Signed-off-by: mgoin <mike.goin12@gmail.com>
Co-authored-by: mgoin <mike.goin12@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 13:58:46 -07:00
Dan Alistarh ed0622e3a8 [Attention] TurboQuant: remove redundant random signs, add prior art attribution (#40194)
Signed-off-by: Dan Alistarh <d.alistarh@gmail.com>
2026-04-18 14:31:59 -04:00
Yusuf Mohammad b5f6c5f834 Added general ND x ND matmul and unit test for it (#39909)
Signed-off-by: Yusuf <yusufmohammad@live.com>
2026-04-18 10:05:21 -04:00
Jee Jee Li bfde49e287 [DOC] Add fuse_minimax_qk_norm (#39782)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2026-04-18 00:41:37 -07:00
Nick CaoandClaude 153ba7f0f3 [Refactor] Drop direct dependency on librosa (#39079)
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-04-18 06:55:38 +00:00
Chinmay-Kulkarni-AMD 87518c3027 [ZenCPU] AMD Zen CPU Backend with supported dtypes via zentorch weekly (#39967)
Signed-off-by: Chinmay Kulkarni <Chinmay.Kulkarni@amd.com>
2026-04-18 06:22:37 +00:00
Rishapveer Singh aeee7ef939 [Bugfix] Fix k_proj's bias for GLM-ASR (#40160)
Signed-off-by: Rishapveer Singh <singhrishapveer@gmail.com>
2026-04-17 22:34:33 -07:00
z1ying cda19ecf4d [Doc] Fix outdated source reference comment in anthropic/serving.py (#40189)
Signed-off-by: z1ying <tzzying@outlook.com>
2026-04-17 22:31:13 -07:00
Nithin ChalapathiandCyrus Leung 80b18230e0 [Frontend] Add multimodal support to /inference/v1/generate endpoint (#38405)
Signed-off-by: Nithin Chalapathi <nithin.ch10@gmail.com>
Signed-off-by: Nithin Chalapathi <nithinc@berkeley.edu>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2026-04-17 20:31:56 -07:00
z1ying d0697cc7b6 [Doc] Add Realtime Transcription section to supported_models.md (#39845)
Signed-off-by: Ziying Tao <tzzying@outlook.com>
2026-04-18 03:26:14 +00:00
milesialandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> b0755523dc [Core] Reduce mm scheduler, get_num_embed overhead (#40143)
Signed-off-by: milesial <milesial@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-04-18 11:25:49 +08:00
Chaojun Zhangandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 993859ceb0 [XPU] fix all_reduce all-zero accuracy issue under torch.compile (#39844)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-04-18 02:33:07 +00:00
Michael Goin 48a65ccb02 [CI] Speed up test_fused_marlin_moe (#40178)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
2026-04-17 19:26:21 -07:00
Xinyu ChenandKunshang Ji 55842a8d69 [XPU]fake impl for xpu fp8_gemm (#39984)
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-04-18 08:53:56 +08:00
Michael Goin 1f45e83756 Remove outdated tests test_mixtral_moe and test_duplicated_ignored_sequence_group (#40175)
Signed-off-by: mgoin <mgoin64@gmail.com>
2026-04-17 16:49:43 -07:00
Michael Goin a8bffaa133 [Kernel] Add MXFP4 W4A4 CUTLASS MoE kernel for SM100 (#37463)
Signed-off-by: mgoin <mgoin64@gmail.com>
2026-04-17 16:42:32 -07:00
Yanan CaoandClaude Sonnet 4 5cdddddd4a [Kernel] [Helion] Force disable HOP path due to performance regression (#40171)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Sonnet 4 <noreply@anthropic.com>
2026-04-17 17:36:49 -04:00
aditi-amd 6ef1efd51f [ROCm] Fix TurboQuant on ROCm: backend routing, flash-attn compat, int64 overflow (#39953)
Signed-off-by: aditi <aditi.rana@amd.com>
2026-04-17 13:08:37 -07:00
Ryan Rock 58da4ee047 [AMD][CI] Update DeepEP branch (#38396)
Signed-off-by: Ryan Rock <ryan.rock@amd.com>
2026-04-17 14:30:20 -05:00
Andreas Karatzas 1ae11e2bfc [ROCm][CI] Build fastsafetensors from source so it links against libamdhip64 (#39978)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-04-17 14:30:08 -05:00
Xinyu ChenandKunshang Ji 251c18d1f8 skip fp8e4b15 on xpu (#39957)
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-04-17 16:55:08 +00:00
Roger WangandChauncey 512765d52d [Misc][UX] Map mimo reasoning and tooling parsers (#40089)
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
2026-04-17 16:49:21 +00:00
allgatherandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 640cc9dd7d feat: Add LoRA support for Gemma4ForConditionalGeneration (#39291)
Signed-off-by: allgather <all2allops@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-04-17 09:39:19 -07:00
Jared Wenandsfeng33 ceade1952c [BugFix] Support custom tool parsers when tool_choice is required and named function (#39870)
Signed-off-by: JaredforReal <w13431838023@gmail.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: sfeng33 <4florafeng@gmail.com>
2026-04-17 16:38:10 +00:00
Jing WangandCopilot 747256bb5d [Bugfix][Core] Fix stuck chunked pipeline parallelism with async scheduling (#38726)
Signed-off-by: Jing Wang <jingwang96@qq.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-04-17 16:02:50 +00:00
Michael Goin 1174723eba Fix TURBOQUANT backend selection in cuda.py (#40060)
Signed-off-by: Michael Goin <mgoin64@gmail.com>
2026-04-17 07:31:41 -07:00
sychen52 6b2b7bd0eb Add nvfp4 support to reshape_and_cache_flash (#37332)
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
2026-04-17 07:28:00 -07:00
Ben Browning 70770268c3 Add @bbrowning to CODEOWNERS (#40141)
Signed-off-by: Ben Browning <bbrownin@redhat.com>
2026-04-17 09:51:48 -04:00
Chauncey 7a51b3e415 [Bugfix] Fix empty delta detection in Qwen3XMLToolParser streaming (#40090)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2026-04-17 13:34:55 +00:00
Li, Jiang d02421a7db [CPU] Refactor CPU affinity and memory management (#39781)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2026-04-17 21:01:08 +08:00
Lukas Geiger b1dc87a098 [Models][Gemma4] Prevent GPU/CPU sync in embed_input_ids (#39234)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
2026-04-17 12:37:21 +00:00
Or Ozeri 79a5b63253 [kv_offload]: Fix num CPU blocks for UniformTypeKVCacheSpecs (#39617)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
2026-04-17 15:13:55 +03:00
Maral c0c98b8b9a [Bugfix] Add Marlin kernel in block scaled mm kernel selection. (#40105)
Signed-off-by: maral <maralbahari.98@gmail.com>
2026-04-17 10:20:32 +00:00
wang.yuqi 8d2cff8140 [Examples] Resettle Observability examples. (#40123)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-04-17 03:13:31 -07:00
Cyrus Leung 4f436782af [Misc] Improve new PR bot trigger condition (#40114)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-04-17 16:56:22 +08:00
z1ying bf45e6d0a5 [Doc] Add Gemma 4 to supported models list (#39607)
Signed-off-by: z1ying <tzzying@outlook.com>
Signed-off-by: Ziying Tao <tzzying@outlook.com>
2026-04-17 13:42:52 +08:00
wang.yuqiandMichele Gazzetti 978a4462bb [CI Failure] Fix Plugin Tests (2 GPUs) Failure (#40083)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: Michele Gazzetti <michele.gazzetti1@ibm.com>
2026-04-17 04:17:39 +00:00
Michael Goin 1948d0c467 [UX] Defer some imports on CLI paths to save ~2s (#40056)
Signed-off-by: mgoin <mgoin64@gmail.com>
2026-04-16 19:48:37 -07:00
Shinichi Hemmi 4c47710bf7 [CI/Build] Apply ruff formatter to pass pre-commit (#40078)
Signed-off-by: Hemmi Shinichi <shemmi@preferred.jp>
2026-04-17 08:54:32 +08:00
Giancarlo Delfin bf9a5ddb24 [MLA] Optimize mla indexer prepare uniform decode for MTP > 1 (#39458)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
2026-04-16 16:27:51 -07:00
bnellnm 79e799ebbd [Bugfix] Temporarily disable B200 fp4 MoE layer tests (#40057)
Signed-off-by: Bill Nell <bnell@redhat.com>
2026-04-16 19:26:55 -04:00
Netanel Haber c4e601c73c Bugfix: Parakeet: .conv.pointwise/depthwise_conv1/2.bias weigths can exist even if convolution_bias=False (#40007)
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
2026-04-16 23:22:05 +00:00
BadrBasowid 29057d3bee [Compilation] Add Unit Tests for VllmFusionPatternMatcherPass (#39692)
Signed-off-by: BadrBasowid <badr.basowid@gmail.com>
2026-04-16 22:57:16 +00:00
Matthew Bonanni 219bb5b8c0 [Misc] Update committers.md (#40058)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2026-04-16 13:48:41 -07:00
Asaf Gardin ad2b1277f9 [Quantization] Consolidate experts_int8 with fp8 online quantization (#38463)
Signed-off-by: Josephasafg <ajgard7@gmail.com>
2026-04-16 13:12:20 -07:00
roikoren755 b897f00c9c Gate SSU dispatch setup (#40039)
Signed-off-by: Roi Koren <roik@nvidia.com>
2026-04-16 13:06:01 -07:00
adf9bb3c57 [CI] Add weight transfer tests to CI (#39821)
Signed-off-by: SumanthRH <sumanthrh99@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2026-04-16 15:51:45 -04:00
Flora Feng b16fda62b7 [Misc] Add @sfeng33 to CODEOWNERS (#40048)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-04-16 12:25:29 -07:00