Commits · 19bee6d12d985c231b16374c99836376fc0c5706 · OpenDAS / vllm_cscc

"examples/vllm_v0/vscode:/vscode.git/clone" did not exist on "3f53a78e036721d367f8cbf9b3087de8b8666059"

03 Dec, 2025 21 commits

[Performance][DP/EP] Add silu_mul_per_token_group_quant_fp8_colmajor kernel (#29470) · 19bee6d1

Varun Sundar Rabindranath authored Dec 03, 2025

Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

19bee6d1

[Bugfix] Mistral tool parser streaming update (#19425) · dd5d1ef7

avigny authored Dec 03, 2025


Signed-off-by: avigny <47987522+avigny@users.noreply.github.com>
Signed-off-by: Chauncey <chaunceyjiang@gmail.com>
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Jeff Cook <jeff@jeffcook.io>
Co-authored-by: sfbemerk <benjaminmerkel@mail.de>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

dd5d1ef7

SigLIP example add chat_template (#29902) · 9ae3c55b
Yu Jiaqi authored Dec 04, 2025
```
Signed-off-by: piood <2477084691@qq.com>
```
9ae3c55b

[Core] Add xxHash as a high-performance hash option for accelerating prefix caching (#29163) · 9bcf9229

Lumis Chen authored Dec 04, 2025


Signed-off-by: LuminolT <lumischen01@gmail.com>
Signed-off-by: Lumis Chen <lumischen01@gmail.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>

9bcf9229

[Frontend] supports deepseekv32 chat template (#29837) · b78772c4
Chauncey authored Dec 03, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
b78772c4
[docker] Build CUDA kernels in separate Docker stage for faster rebuilds (#29452) · f5d3d93c
Amr Mahdi authored Dec 03, 2025
```
Signed-off-by: Amr Mahdi <amrmahdi@meta.com>
```
f5d3d93c

[refactor] CTMoEMethods to use QuantizationArgs (#28871) · b294e28d

HDCharles authored Dec 03, 2025


Signed-off-by: HDCharles <charlesdavidhernandez@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

b294e28d

[Bugfix] Follow-up fix on MediaWithBytes (#29951) · 787b84a9
Roger Wang authored Dec 03, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
787b84a9
[Bugfix][Quantization] Support BF16 tensors on GGUF (#29948) · 42c19496
Tsukasa OI authored Dec 03, 2025
```
Signed-off-by: Tsukasa OI <floss_llm@irq.a4lg.com>
```
42c19496

[Bugfix] Fix incorrect `image_grid_thw` rank for HunyuanOCR from missing... · a21cd9ed

Isotr0py authored Dec 03, 2025


[Bugfix] Fix incorrect `image_grid_thw` rank for HunyuanOCR from missing `merge_by_field_config=True` (#29950)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

a21cd9ed

[CI] Add Async Eplb nightly CI tests (#29385) · 7fe9c1a2

WeiQing Chen authored Dec 03, 2025


Signed-off-by: David Chen <530634352@qq.com>
Signed-off-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

7fe9c1a2

[Refactor] [1/N] to simplify the vLLM serving architecture (#28040) · 3f42b05f
Chauncey authored Dec 03, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
3f42b05f
Add logging for cudagraph related info (#29825) · 69520bc6
Yong Hoon Shin authored Dec 02, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
69520bc6
[responsesAPI] support input output messages for non harmony models (#29549) · 3a775148
Andrew Xia authored Dec 02, 2025
```
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
```
3a775148
[Misc] Allow `fetch_*` utils to access local files by default (#29932) · bbfb55c2
Cyrus Leung authored Dec 03, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
bbfb55c2
[BugFix] fix imgs_pos in hunyuan_vl (#29879) · 0bec63fa
JackieWu authored Dec 03, 2025
```
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
0bec63fa

[Bugfix] Defunctionalize TRTLLM AR+Norm op for avoiding extra clone kernel before it (#29631) · c719c405

elvischenv authored Dec 03, 2025

Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

c719c405

[Docs] Discuss api key limitations in security guide (#29922) · b08025a8
Russell Bryant authored Dec 02, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
b08025a8

[Core] Rename PassConfig flags as per RFC #27995 (#29646) · d7284a26

Arpit Khandelwal authored Dec 02, 2025


Signed-off-by: arpitkh101 <arpit5khandelwal@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

d7284a26

[Bugfix] Fix regression on pooling models from PR#29621 (#29921) · 4dd79783

Roger Wang authored Dec 02, 2025


Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

4dd79783

[BugFix] Fix assert in `build_for_cudagraph_capture` (#29893) · 5cdd6645
Lucas Wilkinson authored Dec 02, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
5cdd6645

02 Dec, 2025 19 commits

[Doc] Add allocate_slots parameter docs (#29777) · 5d91d2b2

maang-h authored Dec 03, 2025


Signed-off-by: maang <maang_h@163.com>
Signed-off-by: maang-h <55082429+maang-h@users.noreply.github.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>

5d91d2b2

[BUGFIX] Fix regex pattern for Mistral Tool Call (#29918) · 1b1e35aa
Julien Denize authored Dec 02, 2025
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
1b1e35aa
[BUGFIX] llama_4_scaling wrongly passed to DeepseekAttention (#29908) · 5e5646e2
Julien Denize authored Dec 02, 2025
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
5e5646e2

[Bugfix] fix --scheduling-policy=priority & n>1 crashes engine (#29764) · 0a9caca9

Chauncey authored Dec 03, 2025


Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

0a9caca9

[Bugfix][EPLB] Prevent user-provided EPLB config from being overwritten with defaults (#29911) · e6f114ac
Sage Moore authored Dec 02, 2025
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
e6f114ac
Fix some more Transformers nightly tests (#29872) · 6fc5841d
Harry Mellor authored Dec 02, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
6fc5841d
[Perf] Avoid pageable HtoD transfer in MinTokensLogitsProcessor (#29826) · 1528e079
jthomson04 authored Dec 02, 2025
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
```
1528e079

Fix boolean nested params, add dict format support, and enhance plotting for... · 1c593e11

Copilot authored Dec 02, 2025

Fix boolean nested params, add dict format support, and enhance plotting for vllm bench sweep (#29025)
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ProExpertProg <11367180+ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

1c593e11

feat(model): Add BitsAndBytes quantization support for Qwen3-Omni-MoE (#29896) · a2b053dc
Navanit Dubey authored Dec 03, 2025
```
Signed-off-by: navanit-git <navanitdubey@gmail.com>
```
a2b053dc
[Attention][CUDAGraph] Remove CG padding from attention backends (#29352) · 1d93f116
Matthew Bonanni authored Dec 02, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
1d93f116
[Chore]: Reorganize gguf utils funtions under `transformers_utils` (#29891) · 63b1da76
Isotr0py authored Dec 03, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
63b1da76
[responsesAPI][3] ResponsesParser to set up non harmony MCP (#29413) · 52cb349f
Andrew Xia authored Dec 02, 2025
```
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
```
52cb349f

[Bugfix] Fix incorrect channel order for idefics3 in edge case (#29881) · 0ec84221

Isotr0py authored Dec 03, 2025

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

0ec84221

[Bugfix] Fix DeepSeek R1 MTP weight loading (#29545) · 51c57b51

Matthew Bonanni authored Dec 02, 2025


Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>

51c57b51

[Multimodal][Core] Optimize multimodal preprocessing cache by hashing image... · 60c3d413

ImaGoodFella authored Dec 02, 2025


[Multimodal][Core] Optimize multimodal preprocessing cache by hashing image bytes instead of pixel values (#29621)
Signed-off-by: Rahul Steiger <rasteiger@ethz.ch>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

60c3d413

[Chore] Use `tokenizer.encode` and `tokenizer.decode` directly (#29851) · 68ffbca7
Cyrus Leung authored Dec 02, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
68ffbca7
Remove default values from `InitVar`s so that they're not stored (#29859) · 951445a5
Harry Mellor authored Dec 02, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
951445a5

Add Mistral Large 3 and Ministral 3 (#29757) · d8c6210e

Julien Denize authored Dec 02, 2025


Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Mickael Seznec <mickael@mistral.ai>

d8c6210e

[BugFix] add max-num-batched-token to scheduler hash (#29829) · 70fb77b4
Boyuan Feng authored Dec 02, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
70fb77b4