 Harry Mellor
|
ae098abe3f
|
[CI] Fix some errors on main (#47726)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-06 19:40:23 +00:00 |
|
|
Andrii SkliarandAndrii Skliar
|
b1384f5ec6
|
Enable B12x backend for non-gated MoEs (like Nemotron) (#43328)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
|
2026-07-06 12:40:07 -07:00 |
|
|
Nathaniel McVicarandHarry Mellor
|
b136cc2c2c
|
[Bugfix][Model] Add stability window to DiffusionGemma to match HF stability_threshold semantics (#45965)
Signed-off-by: Nathaniel McVicar <namcvica@microsoft.com>
Signed-off-by: Nathaniel McVicar <Nathaniel.McVicar@microsoft.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-06 19:39:12 +00:00 |
|
|
|
9fde043f54
|
[Kernel][Helion][1/N] Add Helion kernel for silu_and_mul_per_block_quant (#43994)
Signed-off-by: Sean Chen <seachen@redhat.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-07 00:19:01 +08:00 |
|
|
|
24dd2aec81
|
[Bugfix] Preserve FP8 indexer WK pairs across incremental load_weights (#46168)
Signed-off-by: lcheng <lcheng321@gatech.edu>
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-07-06 09:16:46 -07:00 |
|
|
Harry Mellorandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
5bce653e09
|
Make the Transformers modeling backend as fast as native vLLM (#47187)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-06 16:59:14 +01:00 |
|
|
|
5ad11172b7
|
[perf]Add fused Kimi image preprocessing (#47416)
Signed-off-by: Kevin-XiongC <kevin_xiong1997@outlook.com>
Signed-off-by: Kevin_Xiong <kevin_xiong1997@outlook.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-07-06 08:46:32 -07:00 |
|
|
Wentao Ye
|
f70caef48b
|
[Perf] Cache token_to_req_indices for dsv4, 5x~6x kernel performance improvement (#47474)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-07-06 11:17:46 -04:00 |
|
|
|
8d8ec38361
|
[Bugfix][Spec Decode] Add missing draft_id_to_target_id to DSparkDeepseekV4ForCausalLM (#47429)
Signed-off-by: Laurent-Zhang <zhangdongsheng80@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-06 10:55:47 -04:00 |
|
|
Wentao Ye
|
b1c6dba558
|
[Refactor] Remove multiple dead code (#47329)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-07-06 07:54:08 -07:00 |
|
|
jescoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
598d51153a
|
[Bugfix][Distributed] Delegate MNNVL allreduce one-shot selection (#47589)
Signed-off-by: jesco-absolut <team@srswti.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-06 07:47:06 -07:00 |
|
|
Yifan Qiao
|
095adf1fdc
|
[Bugfix] Fix int32 overflow in triton_decode_attention page offsets (#47671)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-07-06 10:36:15 -04:00 |
|
|
Ting SUNandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
373eb314af
|
[Bugfix][Core] Fix num_output_placeholders underflow with async scheduling + spec decode (#46066)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-06 13:50:38 +00:00 |
|
|
Kunshang JiandHarry Mellor
|
07f9baf756
|
Revert "[Platform] Replace torch.cuda.Event with torch.Event (#47140)" (#47668)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-06 14:18:33 +01:00 |
|
|
Ayushman SinghandBenjamin Chislett
|
7a90eb98ab
|
[Bugfix] [Gemma4] Fix Gemma4 MTP draft model layers ignoring quant_config (#47091)
Signed-off-by: Ayushman Singh <40520701+ayush1399@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-07-06 14:04:00 +01:00 |
|
|
Artur Fierkaandquinnlp
|
8b79971bb9
|
attention: pass None for unused args in unified attention TD path (#43597)
Signed-off-by: Artur Fierka <artur.fierka@intel.com>
Co-authored-by: quinnlp <quinnlp@users.noreply.github.com>
|
2026-07-06 21:01:21 +08:00 |
|
|
Qiming Zhang
|
98e4726a14
|
[fix][run_batch]: respect proxy env vars when downloading media URLs (#47697)
Signed-off-by: mauyuyuace <qiming1.zhang@intel.com>
|
2026-07-06 12:45:48 +00:00 |
|
|
BadrBasowid
|
740f379fae
|
[ROCm][AITER] Directly Implement AITER Custom All-reduce in CudaCommunicator (#46065)
Signed-off-by: BadrBasowid <badr.basowid@gmail.com>
|
2026-07-06 12:16:32 +00:00 |
|
|
Alexis K.
|
40cc2e8327
|
[Bugfix] Return HTTP 422 for unprocessable image URLs instead of 500 (#47165)
Signed-off-by: Alexis Kinsella <alexis.kinsella@gmail.com>
|
2026-07-06 11:56:23 +00:00 |
|
|
Juan Pérez de Algabaandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
ba22152096
|
fix(security): block request-level GPU video backend selection withou… (#47259)
Signed-off-by: jperezde <jperezde@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-06 02:36:49 -07:00 |
|
|
Yan Ma
|
90ce3a09be
|
[bugfix] fix MOSS-Audio deepstack_input_embeds initialization in PP (#47607)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-07-06 17:15:50 +08:00 |
|
|
Ma JianandKunshang Ji
|
26c754d847
|
[XPU][Bugfix] Do not transpose weight_scale_inv at load time (#47116)
Signed-off-by: Ma Jian <jian1.ma@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-07-06 17:15:26 +08:00 |
|
|
liuzhenwei
|
736f1a5907
|
[XPU] Route mm_prefix models to Triton attention backend (#47688)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
|
2026-07-06 16:52:44 +08:00 |
|
|
xiaozhoupy
|
d039c17114
|
[Bugfix] Recycle post-final-norm hidden in GLM MTP (single norm) (#47448)
|
2026-07-06 01:07:56 -07:00 |
|
|
Qiming Zhang
|
2fa10566e3
|
[Core][DP] Rotate load-balancer tie-break to avoid systematic engine bias (#47420)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
|
2026-07-06 07:09:16 +00:00 |
|
|
Zhongandzhongjing123
|
98ba9b9583
|
[Frontend] Support OpenAI Responses API namespace tools (#47024)
Signed-off-by: zhongjing123 <jimzhong5193@gmail.com>
Co-authored-by: zhongjing123 <jimzhong5193@gmail.com>
|
2026-07-06 06:21:27 +00:00 |
|
|
LiuTongandClaude
|
16f8110935
|
[Bugfix][CPU][RISC-V] Fix VLEN detection for RVV attention path (#47532)
Signed-off-by: liutong <liutong@iscas.ac.cn>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-06 05:58:03 +00:00 |
|
|
Zhenzhong Xuandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
d9c1767cd4
|
[INC][ARK] Direct Register Custom Op for ARK (#46361)
Signed-off-by: Zhenzhong1 <zhenzhong.xu@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-06 13:45:50 +08:00 |
|
|
Fadi Arafeh
|
f1073c050c
|
[CPU][BugFix] Multiple fixes to w4a8_int8 CPU MoE path (#46739)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
|
2026-07-06 05:39:20 +00:00 |
|
|
alex101-opsandzc02384840
|
f2aaf59151
|
[Feature] Support MTP speculative decoding for Bailing hybrid models (#44880)
Signed-off-by: zc02384840 <zc02384840@antgroup.com>
Co-authored-by: zc02384840 <zc02384840@antgroup.com>
|
2026-07-06 10:38:50 +08:00 |
|
|
Cheng Jiangandchengvjiang
|
95a248faed
|
[Attention Backend] HPC_ATTN backend support mtp and dynamic scheduled attention (#47433)
Signed-off-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: chengvjiang <chengvjiang@tencent.com>
|
2026-07-05 18:18:25 -07:00 |
|
|
|
d2ec433e37
|
[XPU] Fix Eagle3 initialization on XPU (#43957)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-07-06 08:46:05 +08:00 |
|
|
|
78a04c208d
|
[XPU] Fix CUDA API shims breaking Torch Dynamo during AOT compile (#43092)
Signed-off-by: Łukasz Ślusarczyk <lukasz.slusarczyk@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-07-06 08:29:20 +08:00 |
|
|
Isotr0pyandNick Hill
|
cc1d020d01
|
[MRV2] Enable mm prefix bidi attention support on MRV2 (#46942)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-05 14:45:29 +00:00 |
|
|
Ting SUN
|
8974ed89cd
|
[Bugfix][Voxtral Realtime] Fix token feedback timeout silent hang (#44461)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
|
2026-07-05 05:42:36 -07:00 |
|
|
|
fb2faceacd
|
[Bugfix][Model] Fix crash loading Mamba/Mamba2 checkpoints without an architectures field (#46037)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Signed-off-by: Ting SUN <suntcrick@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-05 05:42:32 -07:00 |
|
|
Wentao YeandCanlin Guo
|
b6cc46ec3b
|
[Feature] Support sequence parallel without the need for DP, 1.9%~5.0% E2E Throughput Improvement (#47070)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
|
2026-07-05 05:41:30 -07:00 |
|
|
Lucas Wilkinson
|
fa4321de3d
|
[Bugfix][TurboQuant] Preserve KV cache dtype in backend shape (#47609)
|
2026-07-05 08:20:48 +00:00 |
|
|
Ting SUN
|
9226613043
|
[Bugfix][Pooling] Forward instruction to Jina reranker scoring prompts (#47590)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
|
2026-07-05 05:39:13 +00:00 |
|
|
Luciano MartinsandLuciano Martins
|
34b560b725
|
[Bugfix][Gemma4] Fix FA4 mm_prefix mask: add sliding window and absolute q_idx (#47332)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
|
2026-07-04 17:46:40 -07:00 |
|
|
Ting SUN
|
91b5647300
|
[Bugfix][Model] Allow Run:ai memory_limit sentinel values (#47337)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
|
2026-07-05 00:08:34 +00:00 |
|
|
Ting SUN
|
d2afe39647
|
[Bugfix][Frontend] Preserve default sampling params in batch chat (#47597)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
|
2026-07-04 19:06:39 +00:00 |
|
|
Wentao Ye
|
2a9113f998
|
[Perf] Remove redundant op for GLM 5.2 (#47198)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-07-04 13:25:02 -04:00 |
|
|
yzong-rh
|
0cd6f767e3
|
[Bugfix][Frontend][gpt-oss] Recover raw tail when Harmony parser ends non-terminal (#47379)
|
2026-07-04 10:46:24 -04:00 |
|
|
Harry Mellor
|
f1445f6dbd
|
[CI] Bump huggingface-hub from v1.10.2 to v1.22.0 (#47551)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-04 07:45:45 -07:00 |
|
|
Taneem IbrahimandWentao Ye
|
1d354c694e
|
[Misc] Validate Pooling cache_salt Values (#46966)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-07-04 10:19:28 -04:00 |
|
|
Taneem Ibrahim
|
2f21224527
|
[Misc] Update request-extras parity for batch chat completion (#47333)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-07-04 10:19:04 -04:00 |
|
|
|
fa1fa968c4
|
[Misc] Forward request-level prompt extras for cross-encoder scoring (#46939)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-07-04 10:18:36 -04:00 |
|
|
Taneem Ibrahimandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
6eac8e0070
|
[Misc] Preserve cross-encoder pooling extra kwargs (#47082)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-04 08:14:13 -04:00 |
|
|
Chaojun ZhangandCopilot
|
1a308c449c
|
[XPU] Add W8A8 FP8 linear kernel with multi-granularity quant support (#43645)
Signed-off-by: Chaojun,Zhang <chaojun.zhang@intel.com>
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
2026-07-04 18:10:01 +08:00 |
|