Commits · cf3eacfe58fa9e745c2854782ada884a9f992cf7 · OpenDAS / vllm_cscc

11 Dec, 2025 7 commits
- Standardise `get_rope` to use `rope_parameters["partial_rotary_factor"]`, not `rotary_dim` (#30389) · cf3eacfe
  Harry Mellor authored Dec 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  cf3eacfe
- Add Eagle and Eagle3 support to Transformers modeling backend (#30340) · 8781cd6b
  Harry Mellor authored Dec 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8781cd6b
- Give pooling examples better names (#30488) · 93db3256
  Harry Mellor authored Dec 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  93db3256
- [Misc] Improve error message for `is_multimodal` (#30483) · 3a3b06ee
  Cyrus Leung authored Dec 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  3a3b06ee
- [Deprecation] Remove missed fallback for `embed_input_ids` (#30469) · 13d63b65
  Cyrus Leung authored Dec 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  13d63b65
- [Deprecation] Remove fallbacks for `embed_input_ids` and `embed_multimodal` (#30458) · 979f50ef
  Cyrus Leung authored Dec 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  979f50ef
- Ensure minimum frames for GLM 4.6V compatibility (#30285) · 36c9ce25
  gh-wf authored Dec 11, 2025
```
Signed-off-by: Wayne Ferguson <wayneferguson@gmail.com>
```
  36c9ce25
10 Dec, 2025 3 commits
- [Bugfix] Fix HunyuanOCR cross-image contamination in batch processing (#30344) · e8e8cd73
  Anker authored Dec 10, 2025
```
Signed-off-by: Lennart Brog <lennart.borg@list-ag.de>
Signed-off-by: Anker <20343812+anker-c2@users.noreply.github.com>
```
  e8e8cd73
- [BugFix] Fix minimax m2 model rotary_dim (#30384) · d017bceb
  Roger Young authored Dec 10, 2025
```
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
```
  d017bceb
- [bugfix][quantization] fix quark qwen3 kv_cache quantization (#30308) · 06462392
  haoyangli-amd authored Dec 10, 2025
```
Signed-off-by: Haoyang Li <lihaoyang0109@gmail.com>
```
  06462392
09 Dec, 2025 2 commits

[Model][Quantization] Fix / Add GGUF support for Qwen2 MoE models (#30307) · 73a484ca
Tsukasa OI authored Dec 10, 2025
```
Signed-off-by: Tsukasa OI <floss_llm@irq.a4lg.com>
```
73a484ca

[Bugfix] Qwen 3 VL Embedding loading (#30303) · 9c32df61

wang.yuqi authored Dec 09, 2025

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

9c32df61

08 Dec, 2025 4 commits

Add latent MoE support (#30203) · fcd5306f

shaharmor98 authored Dec 08, 2025


Signed-off-by: Shahar Mor <smor@nvidia.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

fcd5306f

[DeepSeek v3.2] Make top-k work for any logit values. (#27568) · 184076c3

Daniel Cámpora authored Dec 08, 2025


Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

184076c3

[Model][7/N] Improve all pooling task | Deprecation as_reward_model. Extract... · 9e77ffca

wang.yuqi authored Dec 08, 2025


[Model][7/N] Improve all pooling task | Deprecation as_reward_model. Extract hidden states prefer using new multi-vector retrieval API (#26686)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

9e77ffca

[Perf] Remove sync point in vit torch sdpa attn backend (#30232) · bcb6f594
Dazhi Jiang authored Dec 08, 2025
```
Signed-off-by: Dazhi Jiang <dazhi_jiang@163.com>
```
bcb6f594

07 Dec, 2025 2 commits
- Revert "[Renderer] Separate out `RendererConfig` from `ModelConfig` (#30145)" (#30199) · e83b7e37
  Cyrus Leung authored Dec 07, 2025
  
  e83b7e37
- [Renderer] Separate out `RendererConfig` from `ModelConfig` (#30145) · 27f4c2fd
  Cyrus Leung authored Dec 07, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  27f4c2fd
06 Dec, 2025 3 commits
- [Model] Move `multimodal_cpu_fields` definition to field config (#30181) · 671427ef
  Cyrus Leung authored Dec 06, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  671427ef
- [Chore] Deprecate `SupportsMultiModal.merge_by_field_config` (#30170) · c46b932d
  Cyrus Leung authored Dec 06, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c46b932d
- [Model] Add support for transformer-based Ultravox v0.7 projector (#30089) · e858bc4d
  Peter Salas authored Dec 05, 2025
```
Signed-off-by: Peter Salas <peter@fixie.ai>
```
  e858bc4d
05 Dec, 2025 3 commits

[Bugfix][llama4_eagle] Fix missing 'lm_head' attribute (#29926) · 962d7038
Divakar Verma authored Dec 05, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
962d7038

[Attention][UX][1/N] Add AttentionConfig and change attention env vars to CLI arguments (#26315) · 66e674cd

Matthew Bonanni authored Dec 05, 2025

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

66e674cd

[Frontend][Model] Add 'float16' to possible mamba cache dtype values, override... · 6038b1b0

amitz-nv authored Dec 05, 2025


[Frontend][Model] Add 'float16' to possible mamba cache dtype values, override mamba SSM cache dtype value for NemotronH (#29978)
Signed-off-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>

6038b1b0

04 Dec, 2025 8 commits
- Access `partial_rotary_factor` from `rope_parameters` (#29966) · e10c84e0
  Harry Mellor authored Dec 04, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  e10c84e0
- support qwen3-vl handle requests with embeddings (#30037) · 6dcb07f6
  Tao Yun authored Dec 05, 2025
```
Signed-off-by: taoyun <1069423820@qq.com>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  6dcb07f6
- [Chore] Deprecate `merge_by_field_config` arg (#30035) · b286a311
  Cyrus Leung authored Dec 05, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  b286a311
- Delete HF version of Phi 4 MM (#30049) · 9998ea5b
  Harry Mellor authored Dec 04, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  9998ea5b
- [Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145) · 74c4d80c
  wang.yuqi authored Dec 04, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  74c4d80c
- [Misc] Move functions into `PoolingMetadata` (#30027) · 68eb5c8d
  Cyrus Leung authored Dec 04, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  68eb5c8d
- [ROCm] [Bugfix] `compute_attn_mask_seqlen` for qwen3 omni (#29974) · 3f1b0373
  TJian authored Dec 04, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  3f1b0373
- [Misc] Various cleanups for MM input processing (#29970) · 9ae2f603
  Cyrus Leung authored Dec 04, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  9ae2f603
03 Dec, 2025 1 commit

[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

02 Dec, 2025 7 commits

[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
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
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

[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

[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

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