 Andreas Karatzas
|
8adc840c45
|
[ROCm][Test] Use BF16 for Jina v5 nano MTEB test (#50917)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
|
2026-08-04 08:33:05 +08:00 |
|
|
Thien TranandShengqi Chen
|
11f88260a2
|
[Kimi-K3] Migrate FlashKDA to PyTorch stable ABI (#50818)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
|
2026-08-03 17:18:08 -07:00 |
|
|
namgyu-younandClaude Opus 5
|
41ba11b841
|
[Bugfix][Kimi-K3] Enforce packed rows and op availability in AttnRes dispatch (#50567)
Signed-off-by: namgyu-youn <namgyu.dev@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-08-03 17:13:33 -07:00 |
|
|
|
f42761204f
|
llmd+vllm+mori-ep(inter node wide-ep)+mori-io(write) for 2p2d with dp=ep=16 tp=1 (#45043)
Signed-off-by: Shiksha Patel <shikpate@amd.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-04 00:13:15 +00:00 |
|
|
|
c810937573
|
[Kernel] Extend CuTe DSL skinny GEMM to GLM-5.2 (#49791)
Signed-off-by: Peiyuan Zhou <peiyuanzhou1994@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-08-03 16:49:41 -07:00 |
|
|
Ryan HambyandIsotr0py
|
6a9109d865
|
[Bugfix] Fix Qwen3-Omni crash on video with no audio track when use_audio_in_video=True (#48420)
Signed-off-by: RyanJHamby <ryanhamby22@gmail.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-08-03 16:22:00 -07:00 |
|
|
Francesco Fusco
|
c2881ce603
|
[Bugfix][Hybrid] Fix cross-block race on num_accepted in MRv2 align prefix cache (#50432)
Signed-off-by: Francesco Fusco <ffu@zurich.ibm.com>
|
2026-08-03 22:54:24 +00:00 |
|
|
|
0b37d8389f
|
fix: NVFP4 quantization out_dtype should match model dtype, not torch default (#48861)
Signed-off-by: Chris Fontes <2224082+fattchris@users.noreply.github.com>
Co-authored-by: Chris Fontes <chris@fontes.io>
Co-authored-by: Chris Fontes <chris@fontes.dev>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-03 22:47:37 +00:00 |
|
|
Karen Chung
|
f57123aa2d
|
feat(frontend): session id plumbing into requests (#48048)
Signed-off-by: Karen Chung <karenc@nvidia.com>
|
2026-08-03 22:18:58 +00:00 |
|
|
Varun Vinayak ShenoyandNick Hill
|
e578de311c
|
[ModelRunnerV2] Fix scalar Mamba state update with int32 mappings (#50327)
Signed-off-by: Varun Shenoy <varun.vinayak.shenoy@oracle.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-03 22:05:12 +00:00 |
|
|
skysnow2001andDouglas Lehr
|
f43e1d26e3
|
[ROCm] Enable AITER and FP8 inference on GFX120x (#43615)
Signed-off-by: skysnow2001 <skysnow9285@gmail.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
|
2026-08-03 16:45:37 -05:00 |
|
|
Raphaël Rialland
|
4a3447d200
|
[Bugfix][Model Runner V2] Restore multimodal draft capability detection (#50417)
Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai>
|
2026-08-03 14:18:14 -07:00 |
|
|
aoshen02andNick Hill
|
42ab184ea7
|
[MRV2] Enable routed-experts capture (#50721)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-03 21:00:13 +00:00 |
|
|
Andreas Karatzas
|
e279f71583
|
[ROCm][Test] Fix AITER MXFP4 oracle contract (#50728)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-03 20:53:18 +00:00 |
|
|
zcxGGmuandzq
|
c4e9f09de7
|
[Bugfix][Frontend] Reject empty gRPC stop strings (#50746)
Signed-off-by: zq <zhouquan1511@163.com>
Co-authored-by: zq <zhouquan1511@163.com>
|
2026-08-03 20:50:15 +00:00 |
|
|
Francesco FuscoandClaude
|
755513d9a2
|
[Hybrid] Stage the postprocess inputs with a single loop over the request list (#48120)
Signed-off-by: Francesco Fusco <ffu@zurich.ibm.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-03 20:24:22 +00:00 |
|
|
Taneem IbrahimandWentao Ye
|
1c0d207915
|
[Bugfix] Default Gemma3 Model intermediate_tensors to None (#50777)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-08-03 15:07:59 -04:00 |
|
|
Vineeth Sai Varikuntla
|
7f2e78ba4d
|
[Bugfix] Emit a valid media type from encode_{audio,image,video}_url (#49056)
Signed-off-by: Vineeth Sai <vineethsai4444@gmail.com>
|
2026-08-03 19:02:23 +00:00 |
|
|
Hongxia Yang
|
8f50685c48
|
[ROCm][Kimi-K3] aiter moe environment variable cleanup (#50582)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
|
2026-08-03 18:54:04 +00:00 |
|
|
|
952694e384
|
[Bugfix] Validate NIXL speculative config compatibility (#49230)
Signed-off-by: Tzu-Ling <tzulingk@nvidia.com>
Co-authored-by: GPT-5.6 Sol <noreply@openai.com>
Co-authored-by: Cursor Grok 4.5 <noreply@cursor.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-08-04 02:51:04 +08:00 |
|
|
Almog Tavor
|
65cf1276a2
|
[Kernel] Skip fully masked key blocks in windowed Triton prefill (#50776)
Signed-off-by: almogtavor <almogtavor@gmail.com>
|
2026-08-03 18:48:47 +00:00 |
|
|
Andreas Karatzas
|
76d995df2c
|
[CI][ROCm] Export Helion benchmark script in test artifacts (#50726)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-03 13:09:44 -05:00 |
|
|
|
f0de1a604c
|
[Bugfix] Shard UniformTypeKVCacheSpecs block table width under DCP (#50823)
Signed-off-by: Mikhail Kostryukov <mike@triptrack.net>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-08-03 17:34:29 +00:00 |
|
|
|
5df9999fcf
|
[Kimi-K3] Add option to shard the shared expert instead of replicating (#50656)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-08-03 11:41:24 -04:00 |
|
|
wangxiyuan
|
dd11df04f3
|
[Misc] Remove deprecated calculate_kv_scales runtime KV scale calculation (#49389)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
|
2026-08-03 11:15:13 -04:00 |
|
|
Wentao Ye
|
0cf49a5d15
|
[Refactor] Remove multiple dead codes (#50285)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-03 10:59:08 -04:00 |
|
|
Benjamin Chislett
|
68ca6fd02c
|
[Bugfix] Remove bad startup assertion (#50869)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-08-03 14:21:50 +00:00 |
|
|
Nicolò Lucchesi
|
8ba87e0181
|
[CI] Mooncake PD integration tests (#46844)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-08-03 06:55:51 -07:00 |
|
|
Fede KamelharandHarry Mellor
|
005fa01756
|
docs: document reasoning_content output removal as a breaking client change (#50624)
Signed-off-by: fede-kamel <fkamelhar@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-03 13:45:23 +00:00 |
|
|
Kyungmin Leeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
9ae11a6b89
|
[Model] Add K-EXAONE-2.0-750B-A37B (#50524)
Signed-off-by: lkm2835 <lkm2835@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-03 06:33:02 -07:00 |
|
|
|
b977407d8b
|
Support quantized DSpark Markov heads (#50424)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-08-03 05:35:39 -07:00 |
|
|
Nicolò LucchesiandClaude
|
ad0bf3963e
|
[CI] KimiLinear PD in nightlies (#50266)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-03 20:20:41 +08:00 |
|
|
|
ec40f6a8a6
|
[CPU] Fix torch.compile crash from torch.accelerator.synchronize on CPU-only hosts (#49960)
Signed-off-by: R <Ganesh.R@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-08-03 19:48:48 +08:00 |
|
|
Jiangyun Zhu
|
32c42c4f2f
|
[UX] remove torch compile warning when using breakable cudagraph (#50750)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
|
2026-08-03 11:25:49 +00:00 |
|
|
wang.yuqi
|
9acb7b3699
|
[CI] And PPL test for multimodal generation models (#50839)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-08-03 11:25:08 +00:00 |
|
|
Li, Jiang
|
c8602c7906
|
[CPU] Refine CPU kernel dispatch (#50801)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-08-03 17:42:53 +08:00 |
|
|
Jee Jee Li
|
b9d1e2437e
|
K3: Move LatentMoERunner (#50678)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-08-03 09:36:17 +00:00 |
|
|
Christopher MiyaiandHarry Mellor
|
d9dac2b3d4
|
fix: remove stray duplicate from serving benchmark config (#46870)
Signed-off-by: cmiyai <cmiyai@bu.edu>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-03 08:34:12 +00:00 |
|
|
Hareesh GaliandClaude Fable 5
|
89ac407e3d
|
[Perf] Speed up multimodal placeholder and token-match scanning (#50716)
Signed-off-by: Hareesh <hgsata@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-03 08:27:56 +00:00 |
|
|
Juan Pérez de Algaba
|
d83eb0b36b
|
fix(security): classify DeepStream as GPU backend and enforce pixel limits (#50755)
Signed-off-by: jperezde <jperezde@redhat.com>
|
2026-08-03 08:23:09 +00:00 |
|
|
Jee Jee Li
|
4635cc3e8f
|
Shard the K3 Latent-MoE up-projection on large batches (#50383)
|
2026-08-03 00:49:39 -07:00 |
|
|
|
0a6446005d
|
[CPU] Migrate unquantized MoE to the modular-kernel experts structure (#50133)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Fadi Arafeh <fadi.arafeh@arm.com>
|
2026-08-03 14:55:04 +08:00 |
|
|
Cyrus Leung
|
b3f97dae24
|
[Frontend] Require cache_salt to be non-empty via schema (#50816)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-08-03 06:51:27 +00:00 |
|
|
zofiaandKunshang Ji
|
e481da9508
|
[XPU] [Linear] add torch as xpu linear backend (#49664)
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-08-03 14:30:21 +08:00 |
|
|
Qiming Zhang
|
2755489a26
|
[INC] fix w4a4 model (#50807)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
|
2026-08-03 14:28:58 +08:00 |
|
|
|
f5bb701fa2
|
[Bugfix][Frontend] Constrain Anthropic cache_salt to non-empty (#50764)
Signed-off-by: Omkar Shewale <omkarshewale2001@gmail.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
|
2026-08-03 13:33:14 +08:00 |
|
|
YAMAMOTO Takashi
|
5e35a6f4f9
|
cpu_model_runner.py: skip the warm up if CompilationMode.NONE (#50547)
Signed-off-by: YAMAMOTO Takashi <yamamoto@midokura.com>
|
2026-08-03 04:34:29 +00:00 |
|
|
Yifan Qiaoandxijiade.aihemaiti
|
5c4fe4b17e
|
[Bugfix][KV Connector] Propagate EAGLE state across merged Mooncake store groups (#49069)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: xijiade.aihemaiti <3146335281@qq.com>
|
2026-08-02 19:32:26 -07:00 |
|
|
Turner JabbourandClaude
|
e42c230e4f
|
[Bugfix] serving_llama70B_tp4 benchmark was silently running at tensor_parallel_size=1 (#50766)
Signed-off-by: Turner Jabbour <doubleujabbour@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-03 02:26:48 +00:00 |
|
|
Omkar Shewale
|
9a4fd57cac
|
[Model] Support jina-embeddings-v5-text-nano (EuroBERT encoder backbone) (#50688)
Signed-off-by: Omkar Shewale <omkarshewale2001@gmail.com>
|
2026-08-03 01:37:08 +00:00 |
|