Commits · b1c3f96ae3874cc3b5a6bc7e55f43339b81da183 · OpenDAS / vllm_cscc

22 Dec, 2025 16 commits
- [CI][Bugfix] Fix `entrypoints/openai/test_audio.py` (#31151) · b1c3f96a
  Nicolò Lucchesi authored Dec 22, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  b1c3f96a
- [BugFix] skip language model in Encoder (#30242) · 8f8f469b
  dengyunyang authored Dec 22, 2025
```
Signed-off-by: dengyunyang <584797741@qq.com>
```
  8f8f469b
- [CI] add polling for precompiled wheel in python_only_compile.sh, fix index... · 2cf91c2e
  Shengqi Chen authored Dec 22, 2025
```
[CI] add polling for precompiled wheel in python_only_compile.sh, fix index generation for releases (#30781)
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
```
  2cf91c2e
- [gpt-oss] Fix harmony parser in streaming responses (#30205) · bd6d5a74
  AlonKejzman authored Dec 22, 2025
```
Signed-off-by: AlonKejzman <alonkeizman@gmail.com>
```
  bd6d5a74
- [Model] Fix bagel failed to run (#31132) · 256a33ec
  Li Wang authored Dec 22, 2025
```
Signed-off-by: wangli <wangli858794774@gmail.com>
```
  256a33ec
- Update MiniMax-M2 ToolCall and add MiniMax-M2.1 in Docs (#31083) · c02a2705
  Roger Young authored Dec 22, 2025
```
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
```
  c02a2705
- [Bugfix][ROCm] Fix typo: is_linear_fp8_enaled -> is_linear_fp8_enabled (#31109) · cf8eed7b
  Kevin McKay authored Dec 21, 2025
```
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
```
  cf8eed7b
- [Misc] Fix typo: 'occured' -> 'occurred' (#31120) · 44ae85f7
  Kevin McKay authored Dec 21, 2025
```
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
```
  44ae85f7
- [Misc] Fix spelling typos in model comments (#31117) · 14c3e6ad
  Kevin McKay authored Dec 21, 2025
```
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
```
  14c3e6ad
- [Misc] Fix grammar errors in comments and messages (#31115) · 42b42824
  Kevin McKay authored Dec 21, 2025
```
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
```
  42b42824
- [Misc] Fix quantization-related typos (#31116) · ec58c10c
  Kevin McKay authored Dec 21, 2025
```
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
```
  ec58c10c
- [Misc] Fix spelling typos in comments (#31114) · 8c084de5
  Kevin McKay authored Dec 21, 2025
```
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
```
  8c084de5
- [Feature]: Support NVIDIA ModelOpt HF FP8 variants FP8_PER_CHANNEL_PER_TOKEN... · 19cc9468
  CedricHuang authored Dec 22, 2025
```
[Feature]: Support NVIDIA ModelOpt HF FP8 variants FP8_PER_CHANNEL_PER_TOKEN and FP8_PB_WO  in vLLM (#30957)
```
  19cc9468
- [Kernel] Enable fused_qknorm_rope_kernel supports partial rope (#30821) · 097978a1
  Jee Jee Li authored Dec 22, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  097978a1
- [CI] Fix "2 Node Tests (4 GPUs in total)" (#31090) · 7e065eba
  Lucas Wilkinson authored Dec 21, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  7e065eba
- [Doc] Clarify FP8 KV cache computation workflow (#31071) · 9d701e90
  Steve Westerhouse authored Dec 21, 2025
```
Signed-off-by: westers <steve.westerhouse@origami-analytics.com>
```
  9d701e90
21 Dec, 2025 5 commits
- [NVFP4][Perf] Tune NVFP4 input quant kernel for small batch size (#30897) · 06d49028
  Michael Goin authored Dec 21, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  06d49028
- [MoE Refactor][4/N] Marlin Fp8 Mk (#31036) · b471092d
  Robert Shaw authored Dec 21, 2025
  
  b471092d
- ci: add nvidia-smi warmup before Prime-RL integration test (#31093) · 93cabc41
  Ameen Patel authored Dec 21, 2025
```
Signed-off-by: AmeenP <ameenp360@gmail.com>
```
  93cabc41
- add aarnphm and chaunceyjiang to the new tool_parser directory (#31088) · bb80f69b
  Chauncey authored Dec 21, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  bb80f69b
- [BugFix]fix gpt-oss v1/completions response bug (#30608) · 3e92b2b7
  汪志鹏 authored Dec 21, 2025
```
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: bbrowning <bbrownin@redhat.com>
```
  3e92b2b7
20 Dec, 2025 10 commits

[Quantization] add marlin w4a8/w8a8 check (#31061) · 7c73ceb5
Jinzhen Lin authored Dec 21, 2025
```
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
```
7c73ceb5
[CI] Fix H200 Distributed test (#31054) · ae0770fa
Lucas Wilkinson authored Dec 20, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
ae0770fa

[Quantization] support logical_widths for fp8 marlin (#30962) · ee52d990

Jinzhen Lin authored Dec 21, 2025

Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

ee52d990

[MoE Refactor][5/N] Isolate zero expert to LongCatFlash (#28891) · 54c89243

baonudesifeizhai authored Dec 20, 2025

Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Signed-off-by: Dongjie Zou <85092850+baonudesifeizhai@users.noreply.github.com>
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>

54c89243

[XPU] enable fp8 online streaming quantization (#30944) · 560ae963
Yan Ma authored Dec 20, 2025
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
560ae963
[Bugfix] Read truncate_prompt_tokens from pooling_params in AsyncLLM.encode() (#31013) · 1501a407
Jeffrey Wang authored Dec 20, 2025
```
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
```
1501a407
[CI] FIx `fixture 'siglip_attention_config' not found` (#31053) · ff2168bc
Lucas Wilkinson authored Dec 19, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
ff2168bc
[ROCm][CI/Build] Update ROCm dockerfiles (#30991) · 0be14952
Gregory Shtrasberg authored Dec 19, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
0be14952

[Bugfix] fix the alias bug of AttentionBackendEnum when register CUSTOM... · d52c5096

zejunchen-zejun authored Dec 20, 2025


[Bugfix] fix the alias bug of AttentionBackendEnum when register CUSTOM attention backend to vllm (#30869)
Signed-off-by: zejunchen-zejun <zejun.chen@amd.com>

d52c5096

GLM-4.7 Tool Parser and Doc Update (#30876) · 8a7a4143
Yuxuan Zhang authored Dec 20, 2025
```
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
```
8a7a4143

19 Dec, 2025 9 commits
- [MoE Refactor][2/N] Use Modular Kernels for Fp8 (#30825) · 95befecc
  Robert Shaw authored Dec 19, 2025
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  95befecc
- [Bug] Fix `error 'Dynamo failed to run FX node with fake tensors` for Deepseek V3.2 (#31046) · 4cf94298
  Wentao Ye authored Dec 19, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  4cf94298
- [MoE Refactor][3/N] Deprecate cutlass block quant fp8 (b200) (#30990) · 83a317f6
  Robert Shaw authored Dec 19, 2025
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  83a317f6
- [BugFix] Fix TypeError: unhashable type: 'dict' when serving deepseek32 (#30924) · 5f6477d1
  Lucas Wilkinson authored Dec 19, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  5f6477d1
- [Refactor] Refactor for `DeepGemmQuantScaleFMT` using cache (#30898) · 3bd8335b
  Wentao Ye authored Dec 19, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  3bd8335b
- Make engine core client handshake timeout configurable (#27444) · 1ab52135
  Seiji Eicher authored Dec 19, 2025
```
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
```
  1ab52135
- [Model] Add MiMo-V2-Flash support (#30836) · 969bbc7c
  Zhonghua Deng authored Dec 20, 2025
```
Signed-off-by: Abatom <abzhonghua@gmail.com>
Signed-off-by: Jumiar <liuanqim10@126.com>
Signed-off-by: Zyann7 <zyann7@outlook.com>
Co-authored-by: Jumiar <liuanqim10@126.com>
Co-authored-by: Zyann7 <zyann7@outlook.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  969bbc7c
- Update Pytorch version update docs (#30982) · 268a972c
  Andrey Talman authored Dec 19, 2025
  
  268a972c
- [Quantization] fix marlin w8a8 check (#30961) · 5fbfa8d9
  Jinzhen Lin authored Dec 19, 2025
```
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
```
  5fbfa8d9