 Luciano MartinsandLuciano Martins
|
979f5511d7
|
[Bugfix][Gemma4] Keep image bidirectional attention within the sliding window (#47217)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
|
2026-07-02 19:57:41 -07:00 |
|
|
Michael GoinandClaude Fable 5
|
41de1380c2
|
[BugFix] Derive FlashInfer Q dtype from resolved per-group builder state (#47485)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-02 19:33:28 -07:00 |
|
|
Nick Hill
|
276b837dc4
|
[ModelRunner V2][BugFix] Free all model refs on shutdown (#47483)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-02 19:32:48 -07:00 |
|
|
adamkbaranowski
|
4c3c64fcf7
|
Add Laguna XS.2.1 DFlash drafter support (#46853)
Signed-off-by: Adam Baranowski <adam.baranowski@poolside.ai>
|
2026-07-02 18:09:27 -07:00 |
|
|
Harry Mellor
|
e24d1b24fe
|
Fix Transformers modeling backend usage stats (#47472)
|
2026-07-02 12:51:23 -07:00 |
|
|
Dan BlanaruandMatthew Bonanni
|
d29125c085
|
Xqa decode kernels (#43232)
Signed-off-by: Dan Blanaru <48605845+DanBlanaru@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-07-02 12:32:05 -07:00 |
|
|
Michael Goin
|
d715b3aa1e
|
Delete PagedAttention (#47361)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-07-02 12:31:26 -07:00 |
|
|
Joe Rowell
|
258f8de91f
|
[Bugfix][Tool Parser] poolside_v1: accept tool calls without newline after function name (#47311)
Signed-off-by: Joe Rowell <joerowell4@gmail.com>
|
2026-07-02 12:08:37 -07:00 |
|
|
Nick Hill
|
e392bf7a68
|
[BugFix][MRV2] Ensure all req slots are accounted for when scheduling (#46974)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-02 10:19:24 -07:00 |
|
|
Nick Hill
|
443e68cfa6
|
[Bugfix] Fix pooled Whisper encoder sliding-window kernel size (#47437)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-02 10:19:11 -07:00 |
|
|
Chauncey
|
320ee285c9
|
[Model Runner V2][Perf] Warm up GLM-5.2 DSA indexer prefill metadata kernel (#47285)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-07-02 16:31:31 +00:00 |
|
|
Yuxuan Zhang
|
178fd56094
|
support GLM-5.2 gate use FP32 (#47410)
Signed-off-by: zRzRzRzRzRzRzR <Yuxuan.Zhang2@liverpool.ac.uk>
|
2026-07-02 22:45:39 +08:00 |
|
|
Woosuk KwonandClaude Fable 5
|
a47f38f825
|
[Bugfix][Model Runner V2][Spec Decode] Fix int32 offset overflow in block verification kernels (#47383)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-02 07:32:38 -07:00 |
|
|
Nick Hill
|
3e158ae62d
|
[ModelRunner V2] Fix Mamba2 crash on non-spec-decode (#47428)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-02 07:05:16 -07:00 |
|
|
Wentao YeandNick Hill
|
a2f713002d
|
[ModelRunner V2] Enable by default for all dense models (#44443)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-02 18:48:57 +08:00 |
|
|
|
b0b8a286dd
|
[Model] Add LLaVA-OneVision-2 (LlavaOnevision2ForConditionalGeneration) (#44785)
Signed-off-by: chengzheng345 <209475443+chengzheng345@users.noreply.github.com>
Co-authored-by: chengzheng345 <209475443+chengzheng345@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-02 16:41:49 +08:00 |
|
|
|
3af8789559
|
[Feature] Universal speculative decoding for heterogeneous vocabularies (TLI) (#38174)
Signed-off-by: wan-danfeng <wandanfeng0802@gmail.com>
Signed-off-by: Wonderful <wandanfeng0802@gmail.com>
Co-authored-by: Wan_DF <wonderful199082@126.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-07-02 01:34:20 -07:00 |
|
|
Hiki
|
2665ed704b
|
[Bugfix][Kernel] Correct FlashInfer CUTLASS MoE tuning token bound (#46838)
Signed-off-by: Haobin Guo <haobing@nvidia.com>
|
2026-07-02 05:11:00 +00:00 |
|
|
xaguilar-amd
|
09663abde0
|
[ROCm][MLA] Fuse MLA q/kv RMSNorm + FP8 per-token quant in the FP8 attention path (#44977)
Signed-off-by: Xavier Aguilar <xavier.aguilarfruto@amd.com>
Signed-off-by: Xavier Aguilar <Xavier.AguilarFruto@amd.com>
|
2026-07-02 13:00:41 +08:00 |
|
|
Giancarlo Delfin
|
d63c8e9444
|
[BugFix][Spec Decode] Compact shared topk indices buffer after first MTP draft step (#47238)
|
2026-07-01 21:38:51 -07:00 |
|
|
Michael Goin
|
2b753ad200
|
[Spec Decode] DSpark speculators checkpoint support (#47093)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-07-01 17:32:27 -07:00 |
|
|
Yongye ZhuandClaude Opus 4.8
|
fa248139a0
|
[MoE] Plumb gemm1_alpha/beta/clamp_limit into TRT-LLM FP8 MoE (#45723)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-01 14:34:05 -07:00 |
|
|
Yongye Zhu
|
d3229431f9
|
[DSV4] Better MXFP8 quantization kernel (#47229)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-07-01 14:33:51 -07:00 |
|
|
Nick Hill
|
4787f2dd1b
|
[Bugfix] Don't read KV cache past seq_len in triton paged attn kernels (#47305)
|
2026-07-01 12:43:00 -07:00 |
|
|
Nick Hill
|
8cfeb84dba
|
[ModelRunner V2] Warmup cross-attn properly in encoder-decoder case (#47308)
|
2026-07-01 12:36:48 -07:00 |
|
|
Yiliu DongandNick Hill
|
00eb7cefa3
|
[Bugfix] Prevent padding placeholders from reaching embeddings (#47029)
Signed-off-by: qianlihuang <91178480+qianlihuang@users.noreply.github.com>
Signed-off-by: Yiliu Dong <91178480+qianlihuang@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-01 09:26:03 -07:00 |
|
|
Michał Ganczarenko
|
c8bdcc0116
|
[Bench][BugFix] Fix empty decoder prompt for Cohere ASR in throughput benchmark (#47135)
Signed-off-by: Michal Ganczarenko <michal.ganczarenko@intel.com>
|
2026-07-01 15:42:27 +00:00 |
|
|
|
f5a8d73377
|
[Spec Decode] DSpark (#46995)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-07-01 08:30:24 -07:00 |
|
|
Michał GanczarenkoandKunshang Ji
|
63fcce4de1
|
[Bugfix] Fix GraniteMoeShared weight loading broken by #41184 (#47031)
Signed-off-by: <Michal Ganczarenko> <michal.ganczarenko@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-07-01 22:39:12 +08:00 |
|
|
Chaojun Zhang
|
13c49f9845
|
[xpu][lora]: Align LoRA implementation with Punica GPU: fix _apply_expand rank mismatch, add_inputs hardcode, and MoE EP (#45368)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
|
2026-07-01 22:14:04 +08:00 |
|
|
Harry Mellor
|
a78c15616f
|
Migrate GPTBigCode and Starcoder2 to the Transformers modeling backend (#30966)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-01 13:41:36 +00:00 |
|
|
Fangzhou AiandClaude
|
4e5ca89cfe
|
[ROCm][MiniMax-M3] Cross-layer lightning-indexer top-k sharing (#47269)
Signed-off-by: Fangzhou Ai <fangzhouai@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-01 10:50:09 +00:00 |
|
|
Harry Mellor
|
a22e0dfc69
|
[Model] Remove AyaVision, MusicFlamingo (#47263)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-01 10:39:33 +00:00 |
|
|
stevenkuang
|
cc56379e28
|
[Model] Support Hy3 token suffix and JSON Schema array types (#47192)
Signed-off-by: stevenkuang-tencent <stevenkuang@tencent.com>
|
2026-07-01 10:16:07 +00:00 |
|
|
Aleksei IvashovandNickLucche
|
024b06b0dc
|
[Bugfix] Expose usage field in GenerateResponse for disaggregated serving (#42748)
Signed-off-by: AIvashov <ivashov.aleksey@proton.me>
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-07-01 10:00:19 +00:00 |
|
|
Harry Mellor
|
e7d0fcbc09
|
[CI] Fix various failures on main (#47197)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-01 10:35:34 +01:00 |
|
|
akii96
|
aa8bb5562e
|
[ROCm][Perf][Bugfix] DSv4 indexer: use platform FP8 dtype (fnuz) for Q-quant on gfx942 (#46730)
Signed-off-by: Aakif Nawaz <aakif.nawaz@amd.com>
|
2026-07-01 17:33:55 +08:00 |
|
|
Andy Lo
|
fa4bec9056
|
[Bugfix] Fix pooled Whisper sliding-window KV sizing (#47071)
Signed-off-by: Andy Lo <andy@mistral.ai>
|
2026-07-01 11:33:19 +02:00 |
|
|
|
ed41aa270a
|
[ROCm][DSV4] Use aiter mHC pre/post as the default ROCm path (#43950)
Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
Signed-off-by: Fangzhou-Ai <fangzhouai@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-01 16:27:42 +08:00 |
|
|
Aaron HaoandClaude Sonnet 4.6
|
77a9c5ae28
|
Weight sync refactor + move sparse nccl engine (#44353)
Signed-off-by: hao-aaron <ahao@anyscale.com>
Signed-off-by: haoaaron <ahao@anyscale.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-07-01 01:25:19 -07:00 |
|
|
Yejing LaiandKunshang Ji
|
f651a8a9a4
|
[XPU][UT]Enable ut qk_norm_rope_fusion (#42486)
Signed-off-by: Lai, Yejing <yejing.lai@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-07-01 07:38:03 +00:00 |
|
|
Nils Matteson
|
a461070d1c
|
[Core] Make sleep-mode backend capability flags communicator-agnostic (#47243)
|
2026-07-01 07:17:44 +00:00 |
|
|
Tiezhen WANGandClaude
|
4470ae84de
|
Remove mantis (#46806)
Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-01 07:13:58 +00:00 |
|
|
Chauncey
|
697c34b97b
|
[Bugfix] Fix beam search candidate indexing when logprobs count varies (#47126)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-07-01 07:07:06 +00:00 |
|
|
almayneandLi, Jiang <jiang1.li@intel.com>
|
89e99202f2
|
[CPU][Perf]Added tanh AOR for faster gelu activations. (#44639)
Signed-off-by: Anna Mayne <anna.mayne@arm.com>
Signed-off-by: almayne <anna.mayne@arm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-06-30 23:24:40 -07:00 |
|
|
Micah Williamson
|
b446792306
|
[ROCm][Bugfix] Fix Triton "out of resource: shared memory" Error In One-Shot LoRA MoE (#47209)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-06-30 23:24:36 -07:00 |
|
|
Jonathan Mamou
|
df802a87b7
|
[CPU] Remove speculative decoding stream overrides from CPUModelRunner (#47162)
Signed-off-by: jmamou <jonathan.mamou@intel.com>
|
2026-07-01 06:12:49 +00:00 |
|
|
Nils Matteson
|
93d8f834dd
|
[Core] Pluggable sleep-mode backend abstraction (RFC #34303) (#44074)
|
2026-06-30 22:00:53 -07:00 |
|
|
Gabriel Wu
|
9a08a5118e
|
fix: skip cooperative top-K on SM120 (#47164)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
|
2026-06-30 21:32:54 -07:00 |
|
|
|
c5200d3565
|
[Attention][DSA] support dcp for FLASHINFER_MLA_SPARSE (#46076)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jingyi Yang <girasoleyang@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: GirasoleY <girasoleyang@gmail.com>
Co-authored-by: Jingyi Yang <girasoleyang@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-01 00:32:20 -04:00 |
|