 Juan Pérez de Algaba
|
e00a034ad1
|
(security) fix: enforce decoder prompt-length validation for skip-che… (#46588)
Signed-off-by: jperezde <jperezde@redhat.com>
|
2026-08-21 09:07:19 -07:00 |
|
|
Wei-Cheng (Wayne) Chiu
|
b41dc4ec72
|
[Bugfix] Return HTTP 500 for non-streaming generate errors (#49195)
Signed-off-by: WEI CHENG CHIU <waynehacking8@gmail.com>
|
2026-08-21 09:07:17 -07:00 |
|
|
Neil SchemenauerandTyler Michael Smith
|
6dcc5d7cae
|
[Bugfix] Include device index in compile cache paths (#38962)
Signed-off-by: Neil Schemenauer <nas@arctrix.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2026-08-21 09:07:16 -07:00 |
|
|
|
463aa5e30f
|
[ROCm][Perf] Kimi-K3 Fused kernels for KDA prefill (#52606)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-08-21 09:07:13 -07:00 |
|
|
Tiezhen WANGandOpenAI Codex
|
d53b1c2efc
|
Remove native Hunyuan V1 and VL implementations (#53272)
Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-08-21 09:07:10 -07:00 |
|
|
SoluMilken
|
27ec8ac626
|
[Bugfix] Fix MTP draft model using local cache path instead of S3 URL with runai_streamer (#42079)
Signed-off-by: SoluMilken <ypiheyn.imm02g@g2.nctu.edu.tw>
|
2026-08-21 09:07:08 -07:00 |
|
|
|
72aedcc426
|
[DCP] Default query replication for GLM sparse attention (#50382)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-21 09:07:05 -07:00 |
|
|
Hongxia YangandYifan Qiao
|
cd7b7c265a
|
[ROCm] Cpu offload for ROCm 7.13+ to align the hipMemcpyBatchAsync params and perf in 7.14x (#43018)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-08-21 09:07:03 -07:00 |
|
|
DCo
|
c1d7a3808d
|
[Bugfix] Fix HYV3 shared_mlp prefix for compressed-tensors ignore matching (#48682)
Signed-off-by: Xiaoyi Xu <xu_xiaoyi@hotmail.com>
|
2026-08-21 09:07:01 -07:00 |
|
|
ErenAta16
|
fbb17e780b
|
[Bugfix] Fix six quantization exception messages split across positional args (#50479)
Signed-off-by: ErenAta16 <erena6466@gmail.com>
|
2026-08-21 09:06:56 -07:00 |
|
|
Greg Pereira
|
18aa245a99
|
using existing uvicorn configuration for dp supervisor (#52473)
Signed-off-by: Gregory Pereira <grpereir@redhat.com>
|
2026-08-21 09:06:54 -07:00 |
|
|
Bugen ZhaoandOpenAI Codex
|
08b73d07cc
|
[Frontend] Prevent Kimi K3 reserved markers in response text (#52889)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-21 09:06:52 -07:00 |
|
|
Lee Yongjunandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
6f74337c47
|
[Bugfix][Spec Decode]Preserve user --speculative-config overrides for speculators-format models (#42376)
Signed-off-by: leeyongjun <jqueen.astro@gmail.com>
Signed-off-by: Lee Yongjun <35302114+elwhyjay@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-08-21 09:06:47 -07:00 |
|
|
yimdevandusberkeley
|
574e6a00ef
|
[Bugfix][Attention] Normalize FlashInfer prefill LSE before merging (#52796)
Signed-off-by: yimdev <5779256+yimdev@users.noreply.github.com>
Co-authored-by: usberkeley <150880684+usberkeley@users.noreply.github.com>
|
2026-08-21 11:31:14 -04:00 |
|
|
Luke Alonsoandmgoin
|
2740c817ff
|
[Kernel] Add b12x FP4 MoE backend (#52018)
Signed-off-by: Luke Alonso <lalonso@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-08-21 08:04:36 -07:00 |
|
|
shijuzhaoandshijuzhao
|
cda3868f5d
|
[Bugfix] Deterministic MoE combine (reduce_scatterv) under VLLM_BATCH_INVARIANT (#45683)
Signed-off-by: shijuzhao <shijuzhao@tencent.com>
Co-authored-by: shijuzhao <shijuzhao@tencent.com>
|
2026-08-21 21:41:31 +08:00 |
|
|
Harish Gaikwad
|
c8438a3d40
|
[Doc] Fix dead link in KV transfer README (#53230)
Signed-off-by: hagaikwa-redhat <hagaikwa@redhat.com>
|
2026-08-21 12:03:41 +00:00 |
|
|
Shuai ShaoandJee Jee Li
|
a60c66e3dc
|
[Bugfix] Fix int32 index overflow in LoRA punica kernels at long context (#53034)
Signed-off-by: Shuai Shao <ss@rungalileo.io>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-08-21 10:37:06 +00:00 |
|
|
Yan Ma
|
6feafb8b7d
|
[XPU] follow cuda path for mrope on XPU (#53201)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-08-21 10:13:27 +00:00 |
|
|
linitra24
|
e85d1b69cf
|
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
Signed-off-by: linitra24 <Joy25810@foxmail.com>
|
2026-08-21 09:45:54 +00:00 |
|
|
Thanaji Rao ThakkalapelliandKunshang Ji
|
9fd750f00d
|
[XPU][INC] Add int4 w4a8 (dynamic int8 activation) backend for INC linear layers (#50501)
Signed-off-by: Thanaji Rao Thakkalapelli <thanaji.rao.thakkalapelli@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-08-21 14:38:59 +08:00 |
|
|
Wei ZhaoandOpenAI Codex
|
f8e0602713
|
Support kimi k3 nvfp4 checkpoint (#53132)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-21 05:59:44 +00:00 |
|
|
Zihan Zhang
|
b389ac2946
|
[Spec Decode] DFlash2: local convolution + candidate selector (#52816)
|
2026-08-20 22:27:22 -07:00 |
|
|
vhagor
|
ba07e4a48f
|
[Bugfix] Fix batch-invariant fp32 matmul OOR on SM89 for N=1 (#52960)
Signed-off-by: Juqi Li <2223621784@qq.com>
|
2026-08-21 11:46:55 +08:00 |
|
|
|
2785c72a14
|
[Kimi-K3] Extend GEMM-RS to GEMM-AR (#53053)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-08-21 03:44:15 +00:00 |
|
|
Cyrus Leung
|
b00f475f09
|
[MM] Remove text components from ProcessorInputs (#53093)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-08-20 20:42:53 -07:00 |
|
|
Lucas WilkinsonandOpenAI Codex
|
5df31ea52d
|
[Spec Decode] Enable adaptive verification on DSv4 + sm90 (#52795)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-08-20 22:44:55 -04:00 |
|
|
Chauncey
|
c6e19b3be2
|
[Bugfix][Structured Output] Avoid spurious FSM errors after speculative reasoning end (#53046)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-08-21 10:01:06 +08:00 |
|
|
|
91a893de64
|
[Bugfix][Spec Decode] Scope DSpark backend inheritance to DeepSeek V4 (#52809)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-20 18:42:08 -07:00 |
|
|
Kevin H. Luu
|
d29f7f5c92
|
[Bugfix] Load untied Gemma LM head weights (#53170)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
|
2026-08-21 00:47:08 +00:00 |
|
|
|
7cfb97e337
|
[Frontend][Core][Spec Decode] Per-request acceptance stats in OpenAI API responses (#48915)
Signed-off-by: Matthew Kotila <7692737+matthewkotila@users.noreply.github.com>
Co-authored-by: Reed Meyerson <31574681+reed-meyerson@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-08-20 15:42:49 -07:00 |
|
|
MKQuantum
|
2f41c894e3
|
Fix seed loss when batch contains unseeded requests (#51866)
Signed-off-by: MKQuantum <121593006+MKQuantum@users.noreply.github.com>
|
2026-08-20 22:38:53 +00:00 |
|
|
Misha GoinandOpenAI Codex
|
bfb6c13499
|
[Bugfix][MoE] Tune FlashInfer experts to scheduler token limit (#52989)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-20 16:26:24 -04:00 |
|
|
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 |
|
|
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 |
|
|
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 |
|
|
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 |
|
|
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 |
|
|
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 |
|