Commits · 5db8533c30eca34e027f4923ef5e638eedde177b · OpenDAS / vllm_cscc

20 Oct, 2025 1 commit
- remove tbo and zero_overhead envs · 5db8533c
  zhuwenwen authored Oct 20, 2025
  
  5db8533c
15 Oct, 2025 3 commits
- support --no-enable-chunked-prefill of v1 · 573531eb
  zhuwenwen authored Oct 15, 2025
  
  573531eb
- update the layout of weight_loader_v2 in ColumnParallelLinear and update the... · 33f37e9f
  zhuwenwen authored Oct 15, 2025
```
update the layout of weight_loader_v2 in ColumnParallelLinear and update the initialization of is_quantification
```
  33f37e9f
- update linear to matmul · e35a9e99
  zhuwenwen authored Oct 15, 2025
  
  e35a9e99
14 Oct, 2025 1 commit
- update linear apply · 7e5aa0c5
  zhuwenwen authored Oct 14, 2025
  
  7e5aa0c5
13 Oct, 2025 3 commits
- update moe_sum and moe_align · b35a518a
  zhuwenwen authored Oct 13, 2025
  
  b35a518a
- remove --no-enable-chunked-prefill of v1 · 2cf181fd
  zhuwenwen authored Oct 13, 2025
  
  2cf181fd
- disable cascade_attn · 6791e80c
  zhuwenwen authored Oct 13, 2025
  
  6791e80c
12 Oct, 2025 3 commits
- add use_int4_w4a8 of fused_experts · 048f7316
  zhuwenwen authored Oct 12, 2025
  
  048f7316
- remove two_batch_overlap of moe and update use_mla · 11b94900
  zhuwenwen authored Oct 12, 2025
  
  11b94900
- update weight_loader_v2 layout of ColumnParallelLinear and MergedColumnParallelLinear · 6605af8e
  zhuwenwen authored Oct 12, 2025
  
  6605af8e
11 Oct, 2025 2 commits
- remove two_batch_overlap · 88443051
  zhuwenwen authored Oct 11, 2025
  
  88443051
- skip silu_mul_fp8_quant_deep_gemm_cuda and remove zero_overhead · 1bd3ae33
  zhuwenwen authored Oct 11, 2025
  
  1bd3ae33
03 Oct, 2025 1 commit

[Bugfix] Disable cascade attention with FlashInfer (#26130) · d1007767

Michael Goin authored Oct 02, 2025


Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

d1007767

02 Oct, 2025 4 commits

[Deepseek v3.2] Support indexer prefill chunking (#25999) · c75c2e70
Chen Zhang authored Oct 02, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
c75c2e70
[Small] Prevent bypassing media domain restriction via HTTP redirects (#26035) · 9d9a2b77
Chenheli Hua authored Oct 02, 2025
```
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
9d9a2b77

[BugFix] Fix FI accuracy issue when used for MLA prefill (#26063) · 6040e0b6

Lucas Wilkinson authored Oct 02, 2025

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

6040e0b6

[BugFix] ChunkedLocalAttention is currently not CG compatible (#26034) · c536881a
Lucas Wilkinson authored Oct 01, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
c536881a

01 Oct, 2025 10 commits

[BugFix] Fix default kv-cache-dtype default for DeepseekV3.2 (#25988) · e4beabd2
Lucas Wilkinson authored Oct 01, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
e4beabd2
[MM] Add text-only mode for Qwen3-VL (#26000) · a1825fe6
Roger Wang authored Sep 30, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
a1825fe6
[Model] MTP fallback to eager for DeepSeek v32 (#25982) · bab9231b
Lucia Fang authored Sep 30, 2025
```
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
bab9231b
[spec decode] Consolidate speculative decode method name for MTP (#25232) · c214d699
qizixi authored Sep 26, 2025
```
Signed-off-by: zixi-qi <qizixi@meta.com>
```
c214d699
[bugfix][deepseek] fix flashmla kernel selection (#25956) · 83f3c9be
youkaichao authored Oct 01, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
83f3c9be

[NIXL] Add support for MLA caches with different latent dim (#25902) · d0b178ce

Nicolò Lucchesi authored Sep 30, 2025


Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

d0b178ce

[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896) · b3230e1a

Yongye Zhu authored Sep 30, 2025


Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Xiaozhu Meng <mxz297@gmail.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

b3230e1a

[BugFix] Fix DP/EP hang (#25906) · 03df0fb5

Lucas Wilkinson authored Sep 30, 2025


Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

03df0fb5

[Bug] Fix Weight Loading for Block FP8 Cutlass SM90 (#25909) · 9471879b

Wentao Ye authored Sep 29, 2025

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

9471879b

[Bugfix] Fallback ViT attn backend to SDPA for blackwell (#25851) · ab5b6459
Roger Wang authored Sep 28, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
ab5b6459

30 Sep, 2025 7 commits
- fix Z100L&K100 precision error · 913249f9
  zhuwenwen authored Sep 30, 2025
  
  913249f9
- fix pp error and update min_block_size · d95de221
  zhuwenwen authored Sep 30, 2025
  
  d95de221
- when v1 is set to block_size 16, switch to triton implementation · 083ff6ec
  zhuwenwen authored Sep 30, 2025
  
  083ff6ec
- update cat kernel · a4fc4d7e
  zhuwenwen authored Sep 30, 2025
  
  a4fc4d7e
- DeepSeek-R1-Channel-INT8调用rmsquant融合 · 9f087f8b
  zhuwenwen authored Sep 30, 2025
  
  9f087f8b
- [kernels] add rotary_embedding_deepseek_fuse · 1e911dbd
  zhuwenwen authored Sep 30, 2025
```
off rotary_embedding_deepseek_fuse
```
  1e911dbd
- feat: moe_align_block_size 更新lightop 接口,加入对ep的支持 · 63f1c793
  zhuwenwen authored Sep 30, 2025
  
  63f1c793
29 Sep, 2025 2 commits

[P/D] NIXL Updates (#25844) · 8ce5d319

Robert Shaw authored Sep 29, 2025


Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Signed-off-by: rentianyue-jk <rentianyue-jk@360shuke.com>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: rentianyue-jk <rentianyue-jk@360shuke.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Chenheli Hua <huachenheli@outlook.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

8ce5d319

[Bugfix] fix Qwen3VLMoe load when pp > 1 (#25838) · 09c2cbc0

JJJYmmm authored Sep 29, 2025


Signed-off-by: liuye.hj <liuye.hj@alibaba-inc.com>
Co-authored-by: liuye.hj <liuye.hj@alibaba-inc.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

09c2cbc0

28 Sep, 2025 3 commits

[VLM] Update Qwen3-VL max_num_video_tokens calculation for configurable video profiling (#25557) · 4c347044

Isotr0py authored Sep 28, 2025


Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
Signed-off-by: simon-mo <simon.mo@hey.com>

4c347044

[Bugfix] Fix Qwen3-VL regression from #24982 (#25814) · 19e7ab73
Roger Wang authored Sep 27, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
19e7ab73
[MM] Optimize memory profiling for scattered multimodal embeddings (#25810) · 6de3d431
Roger Wang authored Sep 27, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
6de3d431