Commits · 1395461f5fb76145433c1dc8a3b7262ee3799bf8 · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "f954d0715c8b68e780aac4a4f3ffd1ab56bebfcd"

19 Nov, 2025 1 commit

[Hybrid][torch.compile] Refactor mamba2 forward to avoid obscuring linear... · 1395461f

tomeras91 authored Nov 19, 2025


[Hybrid][torch.compile] Refactor mamba2 forward to avoid obscuring linear projections under custom op (#28587)
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>

1395461f

18 Nov, 2025 4 commits
- [Models] Replace all `nn.Conv2d` with vLLM's Conv2dLayer (#28842) · e4bb2684
  Isotr0py authored Nov 19, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  e4bb2684
- [Model] Add Gemma3 GGUF multimodal support (#27772) · c2612371
  Luciano Martins authored Nov 18, 2025
```
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  c2612371
- [Model][Perf] Use cos and sin cache in QwenVL (#28798) · b9489f51
  Canlin Guo authored Nov 18, 2025
```
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
```
  b9489f51
- [Misc] Remove unnecessary parentheses from log statements (#28897) · 0168f69e
  Ning Xie authored Nov 18, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  0168f69e
17 Nov, 2025 3 commits
- [Model] Add Afmoe architecture implementation (#28332) · f77bce00
  Pranav authored Nov 17, 2025
```
Signed-off-by: Maziyar Panahi <maziyar.panahi@iscpif.fr>
Signed-off-by: Pranav <veldurthipranav@gmail.com>
Co-authored-by: Maziyar Panahi <maziyar.panahi@iscpif.fr>
```
  f77bce00
- [Quantization] [Eagle] Add complete quantization support to the draft model in Eagle (#28435) · 95ae50b7
  Shreyas Kulkarni authored Nov 17, 2025
```
Signed-off-by: Shreyas Kulkarni <shreyas.gp269@gmail.com>
```
  95ae50b7
- [BugFix] Fix glm4_moe_mtp load weights bug (#28805) · ab01cd14
  wuyaoxuehun authored Nov 17, 2025
```
Signed-off-by: wuyaoxuehun <798143193@qq.com>
```
  ab01cd14
16 Nov, 2025 3 commits
- [Model][QwenVL] Optimize `Qwen2_5_VisionAttention` q,k preparation (#28769) · 5a87076d
  Lukas Geiger authored Nov 16, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  5a87076d
- Fix gpt oss weight loading with EP + bf16 (#28765) · 8d259fad
  Anna Shors authored Nov 16, 2025
```
Signed-off-by: ashors1 <ashors@nvidia.com>
```
  8d259fad
- Fixed gpt-oss _load_weights_other() parameter position bug (#28715) · af02c409
  Dezhan authored Nov 16, 2025
```
Co-authored-by: Dezhan Tu <dztu@meta.com>
```
  af02c409
15 Nov, 2025 5 commits
- [Model][Qwen3VL] Cache positional embedding indices (#28475) · 07cadab2
  Lukas Geiger authored Nov 15, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  07cadab2
- Add support for Eagle with separate lm-head and embed_tokens layers (#28549) · e439c784
  Eldar Kurtić authored Nov 15, 2025
```
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
```
  e439c784
- [Model] Fix lmhead init bug of bailing_moe (#28777) · 085a5253
  hwhaokun authored Nov 15, 2025
```
Signed-off-by: hwhaokun <haokun0405@163.com>
Co-authored-by: zhaozx-cn <zhaozx2116@163.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  085a5253
- Allow Gemma3 to take image embeddings (#28483) · cb15ee28
  tingtinggithub authored Nov 15, 2025
```
Signed-off-by: tingtinggithub <streamttt@gmail.com>
```
  cb15ee28
- [Model][Qwen3VL] Use `mm_position` to compute mrope positions (#28730) · f05d474c
  Lukas Geiger authored Nov 15, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  f05d474c
14 Nov, 2025 7 commits
- [Bugfix] resolve Qwen3-VL GPTQModel quantized model loading failure (#28663) · cec275ef
  GuanH authored Nov 15, 2025
```
Signed-off-by: GuanH <guansdrailib@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  cec275ef
- LLaMA4 LoRA Adapter Enablement (#28602) · 964d65de
  Fardin Hoque authored Nov 14, 2025
```
Signed-off-by: Fardin Hoque <kfhfar@amazon.com>
Co-authored-by: Wei Wei <wwei6@meta.com>
```
  964d65de
- [Docs] Update the name of `Transformers backend` -> `Transformers modeling backend` (#28725) · 5f3cd7f7
  Harry Mellor authored Nov 14, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  5f3cd7f7
- [Fix] improve aspect ratio in dummy image generation and add common VLM tests... · c934caee
  dongbo910220 authored Nov 15, 2025
```
[Fix] improve aspect ratio in dummy image generation and add common  VLM tests for PaddleOCR-VL (#28711)
Signed-off-by: dongbo910220 <1275604947@qq.com>
```
  c934caee
- [Model] Fix bailing_moe accuracy problem (#28277) · 433c0f86
  zhaozx-cn authored Nov 14, 2025
```
Signed-off-by: zhaozx-cn <zhaozx2116@163.com>
```
  433c0f86
- [Model][MM] Extract conv layer as CustomOp (#28455) · 41b92f7d
  Shanshan Shen authored Nov 14, 2025
```
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  41b92f7d
- [Bugfix] fix dots.ocr pp support (#28705) · c36bcfe6
  Jiangyun Zhu authored Nov 14, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  c36bcfe6
13 Nov, 2025 2 commits
- [BugFix] DeepSeek-OCR: apply NoRepeatNGramLogitsProcessor to greedy path (#28617) · 3035d1a1
  Yuanping Song authored Nov 13, 2025
```
Signed-off-by: Yuanping Song <yuanping.song@outlook.com>
```
  3035d1a1
- Rename clashing method names for vLLM model protocol (#27583) · 97d1c993
  Harry Mellor authored Nov 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  97d1c993
12 Nov, 2025 7 commits
- Skip models that cannot currently init on Transformers v5 (#28471) · 51c599f0
  Harry Mellor authored Nov 12, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  51c599f0
- [Refactor] Remove redundant TP gather/split in split_qkv in QwenVL (#28271) · bc5bd45c
  Canlin Guo authored Nov 12, 2025
```
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
```
  bc5bd45c
- [Bugfix] Fix gpt_oss packed_modules_mapping (#28536) · a9d18b51
  Jee Jee Li authored Nov 12, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  a9d18b51
- [Model] fix glm4_moe_mtp load weights with GLM-4.6 checkpoint. (#27597) · d3ade61e
  wuyaoxuehun authored Nov 12, 2025
```
Signed-off-by: wuao.scotty <wuao.scotty@bytedance.com>
Co-authored-by: wuao.scotty <wuao.scotty@bytedance.com>
```
  d3ade61e
- [BugFix]: --enable-lora with model granite-4.0-micro crash (#27733) · 1761dea1
  yyzxw authored Nov 12, 2025
```
Signed-off-by: zxw <1020938856@qq.com>
```
  1761dea1
- [BugFix] Add fallback path in `apply_rotary_pos_emb_flashattn` for non-cuda platforms (#28447) · b9ce9a30
  Fanli Lin authored Nov 12, 2025
```
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
```
  b9ce9a30
- [Model][Qwen3VL] Simplify `get_mrope_input_positions` using numpy (#28302) · cbb799e3
  Lukas Geiger authored Nov 12, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  cbb799e3
11 Nov, 2025 8 commits
- [LoRA][1/N]Remove LoRA extra vocab (#28382) · 9d1c4747
  Jee Jee Li authored Nov 12, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  9d1c4747
- [BugFix] Fix Siglip2Attention on XPU (#28448) · d5edcb86
  Fanli Lin authored Nov 12, 2025
```
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
```
  d5edcb86
- [Quantization] fix attention quantization of gpt_oss model (#27334) · 5a1271d8
  xuebwang-amd authored Nov 12, 2025
```
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
```
  5a1271d8
- [BugFix] Fix RuntimeError in PixtralHFAttention on CPU/XPU (#28444) · b8860680
  Fanli Lin authored Nov 11, 2025
```
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
```
  b8860680
- [Model] Pass `mm_features` directly into `get_mrope_input_positions` (#28399) · afffd3cc
  Cyrus Leung authored Nov 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  afffd3cc
- [Attention] Refactor CUDA attention backend selection logic (#24794) · b30dfa03
  Matthew Bonanni authored Nov 11, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  b30dfa03
- [Model][Qwen3VL] Slighly speedup `fast_pos_embed_interpolate` (#28434) · 9973e6e0
  Lukas Geiger authored Nov 11, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  9973e6e0
- [BugFix] 'DeepseekV2Config' object has no attribute 'use_mla'` (#28387) · c7991269
  Fanli Lin authored Nov 11, 2025
```
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
```
  c7991269