Commits · a6049be73cb965bad04f6657de6c4d98261a5237 · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "5395471d29f703f19213da629102edc6e9b944be"

12 Oct, 2025 8 commits

[Models][Qwen3VL] Speedup `fast_pos_embed_interpolate` (#26647) · a6049be7
Lukas Geiger authored Oct 12, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
a6049be7
[Feature] Add support for naver/splade-v3 (BERT-based sparse embedding model) (#26339) · 18ed7746
gjgjos authored Oct 13, 2025
```
Signed-off-by: gjgjos <gjgjos@naver.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
18ed7746
Update `Optional[x]` -> `x | None` and `Union[x, y]` to `x | y` (#26633) · 8fcaaf6a
Harry Mellor authored Oct 12, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
8fcaaf6a
[Bugfix][DCP] Set default CUDAGraphMode to PIECEWISE for DCP (#26574) · b91d8db8
Jaya Yuan authored Oct 12, 2025
```
Signed-off-by: FENP <32334296+FENP@users.noreply.github.com>
```
b91d8db8
[Bugfix][CI/Build] Fix failing Mteb CI (#26638) · 045b396d
Isotr0py authored Oct 12, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
045b396d

[MISC] Rename the torch profiler filename as instance_id+rank_id for merging... · 76852017

wang.yuqi authored Oct 12, 2025


[MISC] Rename the torch profiler filename as instance_id+rank_id for merging the Profiler results of each Rank (#25867)
Signed-off-by: wang.yuqi <noooop@126.com>

76852017

[PERF] [Qwen3-next] Speed up gated RMSNorm (#26207) · 82e64c7a

Vadim Gimpelson authored Oct 12, 2025

Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Signed-off-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

82e64c7a

[EPLB] Support ernie4.5-moe (#22100) · c5c8f5ea

Haisheng Chen authored Oct 11, 2025


Signed-off-by: Haisheng Chen <langzs335@outlook.com>
Signed-off-by: Haisheng Chen <60504847+HsChen-sys@users.noreply.github.com>
Signed-off-by: Haisheng Chen <hac048@ucsd.edu>
Co-authored-by: Haisheng Chen <langzs335@outlook.com>

c5c8f5ea

11 Oct, 2025 14 commits
- [compile] Fix inductor partition config (#26645) · 01653a91
  Angela Yi authored Oct 11, 2025
```
Signed-off-by: angelayi <yiangela7@gmail.com>
```
  01653a91
- CP: make correct_attn_out robust to 4‑D views and fix Triton arg binding (#26509) · 0cd103e7
  Huamin Li authored Oct 11, 2025
```
Signed-off-by: Huamin Li <3ericli@gmail.com>
```
  0cd103e7
- [Benchmark] Support Infinity API (#26641) · 5be7ca1b
  Cyrus Leung authored Oct 12, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  5be7ca1b
- [Bugfix] Fix qwen-moe packed_modules_mapping (#26634) · f0a30a06
  Jee Jee Li authored Oct 11, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  f0a30a06
- [Bugfix][Qwen3VL] fix deepstack in qwen3vl (#26626) · 9d6cff3e
  JJJYmmm authored Oct 11, 2025
```
Signed-off-by: liuye.hj <liuye.hj@alibaba-inc.com>
Signed-off-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com>
Co-authored-by: liuye.hj <liuye.hj@alibaba-inc.com>
```
  9d6cff3e
- [compile] Add patched_fused_scaled_matmul_reduce_scatter (#26604) · a25f2ade
  Angela Yi authored Oct 11, 2025
```
Signed-off-by: angelayi <yiangela7@gmail.com>
```
  a25f2ade
- [Refactor]Reduce duplicate code in serving_chat (#26627) · d0bed837
  Chauncey authored Oct 11, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  d0bed837
- [CPU] fix the issue when the node is '-' cause json decode error. (#26562) · f7ee6986
  muzian666 authored Oct 11, 2025
```
Signed-off-by: muzian666 <andylee_2001@163.com>
Co-authored-by: qingan.li <qingan.li@wizpresso.com>
```
  f7ee6986
- Add EAGLE-3 Speculative Decoding Support for Qwen3 MoE (#26485) · d2a71530
  Rahul Tuli authored Oct 11, 2025
```
Signed-off-by: Rahul Tuli <rtuli@redhat.com>
```
  d2a71530
- [Refactor]: Use M-RoPE interface directly while defining model class instead... · 727144be
  dsinghvi authored Oct 11, 2025
```
[Refactor]: Use M-RoPE interface directly while defining model class instead of maintaining model specific M-RoPE implementation in mrope.py (#24172)
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: wwl2755 <wangwenlong2755@gmail.com>
```
  727144be
- [Bugfix][Multi Modal] Fix incorrect Molmo image processing (#26563) · 55392bc8
  sangho.lee authored Oct 11, 2025
```
Signed-off-by: sanghol <sanghol@allenai.org>
```
  55392bc8
- [MM] Move Qwen3Omni MRoPE impl to model file (#26608) · ddaff293
  Roger Wang authored Oct 10, 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>
```
  ddaff293
- [XPU] Upgrade NIXL to remove CUDA dependency (#26570) · 27ed39a3
  liuzhenwei authored Oct 11, 2025
```
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
```
  27ed39a3
- [Frontend] Improve the performance of `is_reasoning_end` (#25735) · be067861
  Chauncey authored Oct 11, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  be067861
10 Oct, 2025 18 commits

[BugFix] Make penalties and bad_words work with async scheduling (#26467) · 5bc26c43
Nick Hill authored Oct 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
5bc26c43
AOT Compilation for torch.compile (Bundled) (#24274) · eef921f4
Zhengxu Chen authored Oct 10, 2025
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
eef921f4
[BugFix] Fix async scheduling + request preemption (#26385) · 949cb017
Nick Hill authored Oct 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
949cb017
[BUG] Qwen3-next MTP. Fix attn metadata build bug (#26564) · e94cfd51
Vadim Gimpelson authored Oct 10, 2025
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
e94cfd51
Fix some typing issues found by `mypy==1.18.2` (#26596) · 7c12763b
Harry Mellor authored Oct 10, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
7c12763b

Add Qwen3-Omni moe thinker (#25550) · 19a9b169

Xiong Wang authored Oct 11, 2025


Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Xiong Wang <feizi.wx@alibaba-inc.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

19a9b169

[Transform] [Quantization] Add QuTLASS support to vLLM (#24440) · 96ad65b7

Roberto L. Castro authored Oct 10, 2025


Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Signed-off-by: Andrei Panferov <andrei@panferov.org>
Co-authored-by: Andrei Panferov <andrei@panferov.org>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

96ad65b7

[Model] Add FlexOlmo model implementation (#24923) · 8d2b8c0f
Shane A authored Oct 10, 2025
```
Signed-off-by: Shane A <shanea@allenai.org>
```
8d2b8c0f

[Model][Qwen3VL] Compute `cu_seqlens` on CPU to remove (#26496) · b2155ed3

Lukas Geiger authored Oct 10, 2025


Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

b2155ed3

[Bugfix] fixed top_logprobs: -1 does not appear to work as intended (#26470) · 910abdbd
Chauncey authored Oct 11, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
910abdbd

[torch.compile] Make inductor partition rules respect splitting_ops #25691 (#25845) · cddce79f

baonudesifeizhai authored Oct 10, 2025

Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

cddce79f

[Metrics] Add test for multi-modal cache stats logging (#26588) · e5192819
Mark McLoughlin authored Oct 10, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
e5192819

Silu v2 (#25074) · 7b03584d

Elvir Crnčević authored Oct 10, 2025


Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: elvircrn <elvircrn@gmail.com>
Signed-off-by: Elvir Crnčević <elvircrn@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>

7b03584d

[Bugfix] Make DP padding optional in coordinate_batch_across_dp (#26375) · ae9d0e7d
Sage Moore authored Oct 10, 2025
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
ae9d0e7d

[BugFix][torch.compile] Fix fused_scaled_matmul_reduce_scatter signature for PyTorch 2.8 (#26038) · f4ba2061

Jason Li authored Oct 10, 2025


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

f4ba2061

[BugFix] Fix noop elimination edge case (#26394) · 67661375
Andy Lo authored Oct 10, 2025
```
Signed-off-by: Andy Lo <andy@mistral.ai>
```
67661375
[Bugfix] Convert untraceable GroupShape to list for AMD impl (#26535) · 213b6445
Lucas Kabela authored Oct 10, 2025
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
213b6445
[NIXL] Ignore abort on already-finished request (#25067) · 784c2311
Mark McLoughlin authored Oct 10, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
784c2311