Commits · da7bc54ea8f44a2dcacc4a9869721bd105006e10 · OpenDAS / vllm_cscc

05 Dec, 2025 17 commits

[responsesAPI][5] ResponsesParser with tools for full MCP python loop (#29798) · da7bc54e

Andrew Xia authored Dec 05, 2025


Signed-off-by: Andrew Xia <axia@fb.com>
Signed-off-by: Andrew Xia <axia@meta.com>
Co-authored-by: Andrew Xia <axia@fb.com>

da7bc54e

[NIXL] Add compatibility checking to NIXL KV connector handshake (#29503) · 949a6a19
Mark McLoughlin authored Dec 05, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
949a6a19

Reduce validation to a warning (#28749) · 2c174420

Alec S authored Dec 05, 2025


Signed-off-by: Alec Solder <alecs@fb.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2c174420

[Compressed Tensors] Add XPU `wNa16` support (#29484) · 0d8a7d8a
Yi Liu authored Dec 05, 2025
```
Signed-off-by: yiliu30 <yi4.liu@intel.com>
```
0d8a7d8a

[Feature] Add Layer-wise NVTX Support (#29990) · c2894d38

Max Hu authored Dec 05, 2025


Signed-off-by: Max Hu <hyoung2991@gmail.com>
Signed-off-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>

c2894d38

[ROCm][MXFP4] Infer w4a4 quant method in rocm aiter fused moe (#29775) · 3628bcaa
Zhiwei authored Dec 05, 2025
```
Signed-off-by: ZhiweiYan-96 <zhiwei.yan@amd.com>
```
3628bcaa
[Bugfix] Fix parse_output_message crash on commentary with no recipient (#29972) · b73b158a
strinczer authored Dec 05, 2025
```
Signed-off-by: Shai Trinczer <strinczer@icloud.com>
Signed-off-by: strinczer <strinczer@icloud.com>
```
b73b158a
[typing] fix type (#29964) · 7ae13c66
Ning Xie authored Dec 05, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
7ae13c66
[bench] Support common prefix len config (for decode-only bench) (#29934) · f16356fe
Ming Yang authored Dec 05, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
f16356fe

[BugFix] Adding env variable to disable async grammar compilation (#29996) · 65ee9728

Alec S authored Dec 05, 2025

Signed-off-by: Alec Solder <alecs@fb.com>
Signed-off-by: Alec S <10566873+alecsolder@users.noreply.github.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>

65ee9728

[Frontend] Remove deprecated -O.xx flag (#29991) · 62b33334
Yanan Cao authored Dec 05, 2025
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
```
62b33334

[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

[Bugfix] Correct num_q_heads on DCP for Flashinfer backends (#29487) · d698bb38

Jingchun Gao authored Dec 05, 2025


Signed-off-by: Jingchun Gao <gaojingchun1@huawei.com>
Signed-off-by: Jingchun Gao <63247409+gjc0824@users.noreply.github.com>
Co-authored-by: Jingchun Gao <gaojingchun1@huawei.com>

d698bb38

Do not guard during noop elimination pass (#30095) · 5867819e
Laith Sakka authored Dec 04, 2025
```
Signed-off-by: Laith Sakka <lsakka@meta.com>
```
5867819e
[PCP&DCP] move CUDAGraph check for PCP&DCP to the check func of platforms (#29952) · 0098a6e3
Qiu authored Dec 05, 2025
```
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
0098a6e3
[Model] Add Holo2 reasoning parser (#30048) · befb59e5
Hubert de La Jonquiere authored Dec 05, 2025
```
Signed-off-by: hdlj-h <hubert@hcompany.ai>
```
befb59e5
[Perf] Enable separate shared_experts stream only for CUDA (#30085) · 4470ee2f
Alexander Matveev authored Dec 04, 2025
```
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
```
4470ee2f

04 Dec, 2025 23 commits
- [aot_compile]change VLLM backend to read fake args from example_value (#29104) · 1f0d1845
  Laith Sakka authored Dec 04, 2025
```
Signed-off-by: Laith Sakka <lsakka@meta.com>
```
  1f0d1845
- [BugFix] Fix DBO assert `assert B_block_table == B_q` (#29933) · c8ab988b
  Lucas Wilkinson authored Dec 04, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  c8ab988b
- [Bugfix] Missing tokens in `return_token_ids` when tool parsers is enabled in... · 48a5fff6
  Peng-YM authored Dec 05, 2025
```
[Bugfix] Missing tokens in `return_token_ids` when tool parsers is enabled in streaming mode (#29074)
Signed-off-by: Peng-YM <1048217874pengym@gmail.com>
```
  48a5fff6
- Abstract eplb algo (#26471) · 1119f6e4
  Mercykid-bash authored Dec 05, 2025
```
Signed-off-by: Che Ruan <cr623@ic.ac.uk>
Signed-off-by: mengxingkongzhouhan <117415539+mengxingkongzhouhan@users.noreply.github.com>
Signed-off-by: Mercykid-bash <ruanche0218@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Che Ruan <cr623@ic.ac.uk>
Co-authored-by: mengxingkongzhouhan <117415539+mengxingkongzhouhan@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  1119f6e4
- 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
- [KVConnector] Remove v0-related kv connector components such as kv pipe and kv... · ece2825a
  Kuntai Du authored Dec 05, 2025
```
[KVConnector] Remove v0-related kv connector components such as kv pipe and kv lookup buffer (#29705)
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
```
  ece2825a
- [Bugfix] Fix FP8 MoE LoRA (#29890) · 652ba93d
  Jee Jee Li authored Dec 05, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  652ba93d
- 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
- [Model Runner V2] Implement get_num_sampled_and_rejected kernel (#30029) · cc050558
  Woosuk Kwon authored Dec 04, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  cc050558
- Use Transformers v5 RoPE standardisation and validation (#30046) · 5c32a06a
  Harry Mellor authored Dec 04, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  5c32a06a
- Fix broken multiline assert in `LoRAModelManager.register_module` (#30032) · dd97e047
  Yongtao Huang authored Dec 04, 2025
```
Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
```
  dd97e047
- 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
- [Bugfix] Fix the issue with interleaved thinking when using streaming (#30033) · 6796ce8b
  Chauncey authored Dec 04, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  6796ce8b
- [ROCm][CI][Bugfix] Fixing the `Multi-Modal Models Test (Extended) 1` group (#30013) · e96a6a6d
  Andreas Karatzas authored Dec 04, 2025
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  e96a6a6d
- Validating Runai Model Streamer Integration with S3 Object Storage (#29320) · 6366c098
  Noa Neria authored Dec 04, 2025
```
Signed-off-by: Noa Neria <noa@run.ai>
```
  6366c098
- [P/D] Introduce Mooncake Transfer Engine as kv_connector (#24718) · 842aba50
  dtc authored Dec 04, 2025
```
Signed-off-by: Tianchen Ding <dtcccc@linux.alibaba.com>
Signed-off-by: dtc <dtcccc@linux.alibaba.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
```
  842aba50
- [Core] Remove forced None assignment for deprecated PassConfig flags (#29994) · dfdda967
  Arpit Khandelwal authored Dec 04, 2025
```
Signed-off-by: arpitkh101 <arpit5khandelwal@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  dfdda967
- Add DeepSeek-V3.2 tool parser. (#29848) · ffdd1811
  Xu Wenqing authored Dec 04, 2025
```
Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com>
```
  ffdd1811
- [ROCm] add fallback for aiter fp8 decode mla (#30005) · b8a6ae41
  Ye (Charlotte) Qi authored Dec 04, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  b8a6ae41
- [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