Commits · 90512b2e8bff5bddca5fca30dc4f0136d682f7d4 · OpenDAS / vllm_cscc

09 Mar, 2026 1 commit
- fix: Use iterator as not to store all the file loads in memory at once (#36149) · 90512b2e
  Shaun Kotek authored Mar 09, 2026
```
Signed-off-by: Shaun Kotek - Nvidia <skotek@nvidia.com>
```
  90512b2e
08 Mar, 2026 2 commits
- Add support for ModelOpt MXFP8 MoE models (#35986) · 0a6a3a12
  danisereb authored Mar 08, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
  0a6a3a12
- [Model] Nano Nemotron VL - fast media preprocessing (#35657) · b7332b05
  nvnbagrov authored Mar 08, 2026
```
Signed-off-by: Natan Bagrov <nbagrov@nvidia.com>
```
  b7332b05
07 Mar, 2026 4 commits
- [Perf] Support FP8 KV cache for Flashinfer MLA Sparse (#35891) · 379689d5
  Wei Zhao authored Mar 07, 2026
  
  379689d5
- Adding support to Sarvam's MoE models (#33942) · 85f50eb4
  rahul-sarvam authored Mar 08, 2026
```
Signed-off-by: rahul-sarvam <140298821+rahul-sarvam@users.noreply.github.com>
```
  85f50eb4
- [Bugfix] Fix compressed-tensors quantization failure for DeepSeek-R1 on MI300x (#36247) · ee8a2951
  vllmellm authored Mar 07, 2026
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
```
  ee8a2951
- mla: don't update kv cache on dummy forwards (#36282) · 24a03915
  Itay Alroy authored Mar 07, 2026
```
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
```
  24a03915
06 Mar, 2026 4 commits
- [CustomOp] CustomOp FusedRMSNormGated (#35877) · f3c6c9c9
  eellison authored Mar 06, 2026
```
Signed-off-by: Elias Ellison <elias.ellison@gmail.com>
Signed-off-by: eellison <elias.ellison@gmail.com>
```
  f3c6c9c9
- [Misc] Lazy import registered processors (#36024) · 1d0c0d20
  Isotr0py authored Mar 06, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  1d0c0d20
- [CI][MM] Gate vision encoder attention mask to MiniCPM only, fixing Aria regression (#36206) · 2a00d324
  Andreas Karatzas authored Mar 06, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  2a00d324
- [Security] Respect user trust_remote_code setting in NemotronVL and KimiK25 (#36192) · 00bd08ed
  Russell Bryant authored Mar 06, 2026
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  00bd08ed
05 Mar, 2026 13 commits
- [Model] Add support for OLMo Hybrid (#32550) · a911f4dd
  Yanhong Li authored Mar 05, 2026
  
  a911f4dd
- [Perf] Optimize FusedMoEModularKernel output tensor using torch.empty (#35794) · f9170209
  Xin Yang authored Mar 05, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  f9170209
- [Bugfix] Disable FlashInfer TRTLLM BF16 path for non-gated MoE (#36146) · 86483ca7
  tomeras91 authored Mar 05, 2026
```
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
```
  86483ca7
- ParakeetProjection.norm = RMSNorm instead of nn.LayerNorm (#36133) · b93a9e6f
  Netanel Haber authored Mar 05, 2026
```
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
```
  b93a9e6f
- [BUGFIX]Fix Qwen-Omni models audio max_token_per_item estimation error leading... · e998fa76
  Avery Miao authored Mar 06, 2026
```
[BUGFIX]Fix Qwen-Omni models audio max_token_per_item estimation error leading to encoder_cache_size is 0 (#35994)
Signed-off-by: Miao, Avery <avery.miao@intel.com>
```
  e998fa76
- [Bugfix][CI] fix typos (#34934) · 6a895197
  Jiayi Yan authored Mar 06, 2026
```
Signed-off-by: 1195343015 <1195343015@qq.com>
Signed-off-by: Jiayi Yan <66017932+1195343015@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6a895197
- refactor funasr model. (#36108) · 3ee68590
  AllenDou authored Mar 06, 2026
```
Signed-off-by: zixiao <shunli.dsl@alibaba-inc.com>
Co-authored-by: zixiao <shunli.dsl@alibaba-inc.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  3ee68590
- [Bugfix] Fix Qwen-VL tokenizer implementation (#36140) · 71963481
  Cyrus Leung authored Mar 06, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  71963481
- Fix import that was moved in Transformers 5.2.0 (#36120) · ecde7af9
  Harry Mellor authored Mar 05, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  ecde7af9
- [Hardware] Replace `torch.cuda.synchronize()` api with `torch.accelerator.synchronize` (#36085) · 66a22096
  Kunshang Ji authored Mar 05, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  66a22096
- [Bugfix] Fix score layer quantization for sequence classification models -... · f600d519
  Hanjun Cho authored Mar 05, 2026
```
[Bugfix] Fix score layer quantization for sequence classification models  - Qwen3 (VL) Reranker (#35849)
Signed-off-by: Hanjun Cho <gkswns0531@gmail.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  f600d519
- Order `config.py` in Lexicographical order (#35866) · 0a12cea2
  Andrii Skliar authored Mar 05, 2026
```
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
```
  0a12cea2
- [Model] Add LoRA support for Whisper models (#29856) · 3b23d57c
  daje0601 authored Mar 05, 2026
```
Signed-off-by: daje0601 <englishmt4118@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  3b23d57c
04 Mar, 2026 16 commits

[Misc] Support OOT linear method registering (#35981) · 562339ab
Shanshan Shen authored Mar 05, 2026
```
Signed-off-by: shen-shanshan <467638484@qq.com>
```
562339ab
[Bugfix] Fix passing of activation_type to trtllm fused MoE NVFP4 and FP8 (#36017) · d7adcadb
amitz-nv authored Mar 05, 2026
```
Signed-off-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>
```
d7adcadb

[UX] Remove NoOpOffloader log (#35678) · b7d59ffc

Robert Shaw authored Mar 04, 2026


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>

b7d59ffc

[Kernel][Mamba] Optimize Mamba2 SSD prefill Triton kernels (#35397) · 7faba503
tomeras91 authored Mar 04, 2026
```
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
```
7faba503
fix minicpmo4.5: fix attn_mask in vit attn && fix resampler pos_emb i… (#34127) · bfdb512f
tc-mb authored Mar 05, 2026
```
Signed-off-by: tc-mb <caitianchi@modelbest.cn>
Co-authored-by: hezhihui <hezhihui@modelbest.cn>
```
bfdb512f
Fix phi4-mm and remove cuda binding (#35964) · 58cfe0dc
Yan Ma authored Mar 05, 2026
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
58cfe0dc
Use MMEncoderAttention (=use FlashAttention) instead of torch.sdpa in radio.py (#35653) · 289fc48a
Netanel Haber authored Mar 04, 2026

289fc48a

[Core] Add All-to-All communication backend for DCP (#34883) · 6cb90109

sungsoo ha authored Mar 04, 2026


Signed-off-by: Sungsoo Ha <sungsooh@nvidia.com>
Signed-off-by: sungsoo ha <hasungsoo@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

6cb90109

[Bugfix][Model] Fix FP8 k_scale/v_scale not loaded for Qwen3-MoE (#35656) · c8c3935b
Raghavan authored Mar 04, 2026
```
Signed-off-by: raghavan <oneraghavan@gmail.com>
```
c8c3935b

[Hardware] Replace `torch.cuda.empty_cache` with `torch.accelerator.empty_cache` (#30681) · 16d2ad1d

Kunshang Ji authored Mar 04, 2026


Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

16d2ad1d

[ROCm][Bugfix] Fall back from CK MXFP4 MoE when GEMM dimensions are unsupported (#35893) · 5dc35387
Chuan (Richard) Li authored Mar 04, 2026
```
Signed-off-by: Li <chuali@amd.com>
```
5dc35387

[Bugfix] Add missing dynamic_arg_dims for Qwen3-ASR torch.compile (#35869) · 36bf2131

Nathan Price authored Mar 04, 2026


Signed-off-by: Nathan Price <nathan@abridge.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

36bf2131

Support Audio Extraction from MP4 Video for Nemotron Nano VL (#35539) · 5d199ac8

Andrii Skliar authored Mar 04, 2026


Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Andrii <askliar@nvidia.com>
Co-authored-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: Andrii Skliar <askliar@oci-nrt-cs-001-vscode-01.cm.cluster>
Co-authored-by: Andrii <askliar@nvidia.com>
Co-authored-by: root <root@pool0-03748.cm.cluster>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: root <root@pool0-02416.cm.cluster>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: root <root@pool0-04880.cm.cluster>

5d199ac8

[Bugfix] Guard mm_token_type_ids kwarg in get_mrope_input_positions (#35711) · edba1504
Andreas Karatzas authored Mar 03, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
edba1504
[Chore] Remove debug code in model implementation (#35883) · 6e9f21e8
Isotr0py authored Mar 04, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
6e9f21e8

[model] support FireRedASR2 (#35727) · c1d96340

AllenDou authored Mar 04, 2026


Signed-off-by: zixiao <shunli.dsl@alibaba-inc.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: zixiao <shunli.dsl@alibaba-inc.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

c1d96340