 Canlin Guo
|
4f6885fffc
|
[DSV4][Kernel] Fuse shared experts into MegaMoE (#53040)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
|
2026-08-20 12:07:02 -07:00 |
|
|
stefankoncarevic
|
3b829cf176
|
[CI/Build][ROCm] Keep the CUDA-only kernel tests out of the ROCm run (#53113)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
|
2026-08-20 13:40:33 -05:00 |
|
|
Thanh Phan
|
d56bbf3995
|
[Bugfix] Support MistralCommonBackend tokenizers in structured output (#52720)
Signed-off-by: Thanh Phan <thanhphantuan1110@gmail.com>
|
2026-08-20 19:08:50 +01:00 |
|
|
kyleliang-nv
|
7c8b68b9ce
|
[Bugfix][MiniMax-M3] Keep FP8 query allocation stable across CUDA graph replay (#51203)
Signed-off-by: Kyle Liang <kylliang@nvidia.com>
|
2026-08-20 10:45:28 -07:00 |
|
|
Isotr0py
|
00f7f25828
|
[Misc] Don't allow language-model-only used with encoder CG together (#53127)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
|
2026-08-20 17:26:47 +00:00 |
|
|
Dennis Yeh
|
ae25628995
|
upgrade tpu-inference to v0.27.0 (#53088)
|
2026-08-20 16:21:39 +00:00 |
|
|
Harry Mellor
|
1fe3a1571a
|
Reduce AutoWeightsLoader kwargs (#53106)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-20 15:40:11 +00:00 |
|
|
Harry Mellor
|
2dd17225c6
|
Fix Transformers modelling backend RMSNormFuser.fuse performance (#52766)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-20 15:21:23 +00:00 |
|
|
|
01af92e175
|
[Feature][Model Runner V2] Support extract_hidden_states speculation (#49811)
Signed-off-by: Zupeng Wang <71580390+zupengwang@users.noreply.github.com>
Signed-off-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: OpenAI <support@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-20 11:13:43 -04:00 |
|
|
Yiqinandshenyiqin
|
cb09dd7488
|
[Core][Multimodal] Skip redundant placeholder scan when token match succeeds (#52925)
Co-authored-by: shenyiqin <shenyiqin1@huawei.com>
|
2026-08-20 15:04:29 +00:00 |
|
|
SeonjinandMisha Goin
|
bd8865a299
|
[Kernel] Add FlashInfer TRTLLM MXFP8 linear backend (#52204)
Signed-off-by: seonjinn <sna@nvidia.com>
Signed-off-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-08-20 10:07:22 -04:00 |
|
|
Prudhvi Vuda
|
de216b6e64
|
[Bugfix] Skip MM processor cache inserts larger than capacity (#53016)
Signed-off-by: Prudhvivuda <prudhvi12042001@gmail.com>
|
2026-08-20 13:42:50 +00:00 |
|
|
Sandeep MaddipatlaandKunshang Ji
|
4b7cb949a9
|
[Docker] Update to nixl-1.3.2 (#51777)
Signed-off-by: Sandeep Maddipatla <sandeep.maddipatla@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-08-20 21:03:32 +08:00 |
|
|
Zupeng Wang
|
df1376907b
|
[Model] Add tower and connector LoRA support for LFM2-VL (#51498)
Signed-off-by: zupengwang <71580390+zupengwang@users.noreply.github.com>
|
2026-08-20 20:33:43 +08:00 |
|
|
Thien TranandOpenAI Codex
|
6259572b28
|
[Docs] Use incremental builds for C++ changes in AGENTS.md (#53098)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-20 04:08:50 -07:00 |
|
|
Kevin H. Luu
|
6df7adc17f
|
[Bugfix][GDN] Reset speculative decode count for an empty draft schedule (#53077)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
|
2026-08-20 10:33:41 +00:00 |
|
|
Harry Mellor
|
f0c14b4f77
|
Fix weight tying (#51665)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-20 10:31:55 +00:00 |
|
|
Harry Mellor
|
6e85feb1b7
|
[3/N] Harden Transformers modelling backend multi-modal path (#51827)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-20 10:24:41 +00:00 |
|
|
Turner JabbourandClaude Sonnet 5
|
1eab6fef01
|
[CI] replace shellcheck script with shellcheck-py hook (#52572)
Signed-off-by: Turner <doubleujabbour@gmail.com>
Signed-off-by: Turner Jabbour <doubleujabbour@gmail.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
|
2026-08-20 10:09:59 +00:00 |
|
|
Ziming Huang
|
5b1e7a812b
|
[BugFix][Mooncake] Fix Mooncake saves from sparse Mamba block tables (#51362)
Signed-off-by: ZeldaHuang <zelda.huanghuang@gmail.com>
Signed-off-by: Ziming Huang <zelda.huanghuang@gmail.com>
|
2026-08-20 03:05:43 -07:00 |
|
|
|
727274a75b
|
[Rust Frontend] Fix Qwen parser auto-detection (#51169)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
|
2026-08-20 09:39:05 +00:00 |
|
|
Eoin-HoustounandClaude Fable 5
|
30e2394c83
|
[Bugfix] Record non-ImportError attention backend probe failures instead of crashing engine init (#51703)
Signed-off-by: Eoin <eoin@turintech.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-20 02:36:00 -07:00 |
|
|
Andreas Karatzas
|
6b68db441e
|
[ROCm] Fix DeepSeek V4 indexer numerics and coverage (#50803)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-20 09:34:00 +00:00 |
|
|
pmanczak
|
44cf3f0466
|
[XPU][Tests] Make tests device-agnostic (#51968)
Signed-off-by: pmanczak <pawel.manczak@intel.com>
|
2026-08-20 02:25:41 -07:00 |
|
|
JC-ut0
|
38e9cefdef
|
[Bugfix] Return HTTP 400 instead of 501 for unknown chat roles in DeepSeek encoders (#53071)
Signed-off-by: JC-ut0 <809602657@qq.com>
|
2026-08-20 09:23:41 +00:00 |
|
|
rongfu.lengandIsotr0py
|
c8de519917
|
[Kernel][Kimi] fused vision q/k roper kernel (#50400)
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-08-20 09:15:47 +00:00 |
|
|
Taneem Ibrahim
|
5d4d470470
|
[CI] Fix nonexistent dependency for data-parallel example test selection (#53026)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-08-20 09:11:00 +00:00 |
|
|
Juan Pérez de Algaba
|
c0a25c089a
|
[Bugfix][Security] Guard _load_ov2_processor with resolve_trust_remote_code (#52952)
Signed-off-by: jperezde <jperezde@redhat.com>
|
2026-08-20 09:09:49 +00:00 |
|
|
|
963fcfa48c
|
[Rust][Benchmark] Align speed-bench CLI flags with Python and add flag parity test (#51592)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: esmeetu <jasonailu87@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-08-20 08:50:51 +00:00 |
|
|
Cyrus Leung
|
4666a8ba9e
|
[Refactor] Remove InputPreprocessor (#53064)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-08-20 08:39:48 +00:00 |
|
|
Anton AandRoger Wang
|
14617c2b6c
|
[Bugfix] DeepEP-V2: expert_tokens_meta must be None on the decode/cudagraph path (empty recv_expert_num_tokens) (#52632)
Signed-off-by: Anton Alexander <dmvevents@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-08-20 01:11:44 -07:00 |
|
|
Kevin H. Luu
|
a34fd69106
|
[CI][Bugfix] Update distributed DP API server test path (#52939)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
|
2026-08-20 01:10:06 -07:00 |
|
|
Quentin GallouédecandBugen Zhao
|
16cfe728d8
|
[Bugfix][Rust Frontend] Reject n > 1 in the /inference/v1/generate route (#52844)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Quentin Gallouédec <quentin.gallouedec@huggingface.co>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-08-20 07:41:06 +00:00 |
|
|
Ankit Nakhawa
|
d66300a1ba
|
[Bugfix][EPD] Fix encoder round-robin fan-out (#52491)
Signed-off-by: AnkitNakhawa <ankitnakhawa@gmail.com>
|
2026-08-20 07:30:40 +00:00 |
|
|
|
a1c5b1fd9f
|
[Core][V1] Support trace_decode_token_ids for deterministic decode replay (#46701)
Signed-off-by: ianzxliu <ianzxliu@tencent.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: Zhixia Liu <liuzhixia.nju@gmail.com>
Co-authored-by: ianzxliu <ianzxliu@tencent.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-20 15:12:43 +08:00 |
|
|
Qiming Zhang
|
754e1c3de4
|
[CI][XPU] Skip test_fused_shared_expert.py on XPU (#53035)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
|
2026-08-20 14:56:09 +08:00 |
|
|
Shanshan Shen
|
d626108b18
|
[ROCm][Perf] Fuse DeepSeek-V4 mHC post/pre and RMSNorm with AITER (#52737)
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
|
2026-08-20 04:51:04 +00:00 |
|
|
akii96
|
cd5035379c
|
[ROCm] [Bugfix] Preserve CPU query offsets during capture (#51585)
Signed-off-by: Aakif Nawaz <aakif.nawaz@amd.com>
|
2026-08-20 12:33:37 +08:00 |
|
|
|
9b2aef5124
|
[Bugfix] Video loading: sample over presentable frames, not header sample count (MP4 edit-list trims) (#48608)
Signed-off-by: AmitMY <amitmoryossef@gmail.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-08-20 04:23:09 +00:00 |
|
|
Xin Yang
|
11baa0ebd8
|
[Attention] Avoid redundant mask compute in GDN metadata build (#52078)
Signed-off-by: Xin Yang <xyangx@amazon.com>
|
2026-08-20 11:52:42 +08:00 |
|
|
Andreas Karatzas
|
4f66bc3e0d
|
[CI][ROCm] Standardize AMD test job labels by device (#52976)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-19 22:33:25 -05:00 |
|
|
Yufeng HeandChauncey
|
e85dd21497
|
fix: report stop_sequence stop_reason in Anthropic Messages API (#45807)
Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
|
2026-08-20 03:23:43 +00:00 |
|
|
pmanczakandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
f85e060ec2
|
[Doc] Update Gaudi HPU committers (#52726)
Signed-off-by: pmanczak <pawel.manczak@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-20 10:59:22 +08:00 |
|
|
|
76fb6d210a
|
[Bugfix][Core] Reserve the KV null block when validating max_model_len (#47272)
Signed-off-by: hyungjun oh <92hyungjun@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-20 02:49:23 +00:00 |
|
|
Woosuk KwonandOpenAI Codex
|
c0233fcf01
|
[Model] Remove unused DeepseekV32Indexer forward (#53021)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-19 19:39:52 -07:00 |
|
|
|
fbb4c04db4
|
[ROCm][CI] Speed up test_rocm_aiter_qk_norm_rope_kvcache_fusion (#53004)
Signed-off-by: Micah Williamson <micah.williamson@amd.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>
|
2026-08-19 21:20:21 -05:00 |
|
|
Woosuk KwonandOpenAI Codex
|
6a962071bd
|
[Distributed] Enable FlashInfer all-reduce by default (#52998)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-19 18:17:43 -07:00 |
|
|
Summer YangandWoosuk Kwon
|
58e5ee0158
|
[refactor] consolidate cp attn ops (#52839)
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-08-19 18:04:11 -07:00 |
|
|
Guanyi Chenandz-zanez
|
bf2866f8bf
|
[KV Connector] Add decode offloading to Mooncake Store consumers (#52466)
Signed-off-by: z-zanez <zhouzh93@mail2.sysu.edu.cn>
Signed-off-by: Guanyi Chen <939416532@qq.com>
Co-authored-by: z-zanez <zhouzh93@mail2.sysu.edu.cn>
|
2026-08-19 17:40:35 -07:00 |
|
|
Giancarlo Delfin
|
d4f4d3f40f
|
[Model Runner V2][Spec Decode] Fix draft logits cache column stride in gumbel_sample (#53017)
|
2026-08-19 17:39:30 -07:00 |
|