Commits · 5782581acfa4dc89491904c7612f076c0cd5a646 · OpenDAS / vllm_cscc

"tests/vscode:/vscode.git/clone" did not exist on "b1098b40723fd3cd02a6e30ca766bde083f61552"

18 Jul, 2025 7 commits
- [Kernel] Apply torch.Tag.needs_fixed_stride_order only for torch==2.6.0 (#19346) · b2eb2b5a
  Richard Zou authored Jul 18, 2025
```
Signed-off-by: rzou <zou3519@gmail.com>
```
  b2eb2b5a
- Let GraniteMoeAttention use YaRN (#21174) · ed8cbfed
  Thomas Parnell authored Jul 18, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  ed8cbfed
- [Core] Set pooling params based on task and model (#21128) · 45badd05
  Cyrus Leung authored Jul 18, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  45badd05
- [Bugfix] Allocate less memory in non-batched CUTLASS MoE (#21121) · 4adc66f6
  ElizaWszola authored Jul 18, 2025
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
```
  4adc66f6
- [Model] Re-add the implicit conversion feature for as_seq_cls_model (#21103) · ca4eb82b
  wang.yuqi authored Jul 18, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  ca4eb82b
- [Core] FlashInfer CUTLASS fused MoE backend (NVFP4) (#20037) · c7d8724e
  Shu Wang authored Jul 17, 2025
```
Signed-off-by: shuw <shuw@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  c7d8724e
- [Log] Debugging Log with more Information (#20770) · 8a8fc946
  Wentao Ye authored Jul 17, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  8a8fc946
17 Jul, 2025 11 commits
- [V0 deprecation] Remove V0 HPU backend (#21131) · 4de71463
  Woosuk Kwon authored Jul 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  4de71463
- [Misc] Qwen MoE model supports LoRA (#20932) · a3a6c695
  Jee Jee Li authored Jul 18, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  a3a6c695
- [Model] Update pooling model interface (#21058) · 90bd2ab6
  Cyrus Leung authored Jul 18, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  90bd2ab6
- [Performance] Performance improvements in non-blockwise fp8 CUTLASS MoE (#20762) · 9fb2d220
  ElizaWszola authored Jul 17, 2025
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
```
  9fb2d220
- [Docs] Improve docstring formatting for `FusedMoEParallelConfig.make` (#21117) · fe8a2c54
  Harry Mellor authored Jul 17, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  fe8a2c54
- [VLM] Add Nemotron-Nano-VL-8B-V1 support (#20349) · 4ef00b5c
  kYLe authored Jul 17, 2025
```
Signed-off-by: Kyle Huang <kylhuang@nvidia.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  4ef00b5c
- [Model] Add ToolParser and MoE Config for Hunyuan A13B (#20820) · 5a7fb3ab
  Asher authored Jul 17, 2025
```
Signed-off-by: Asher Zhang <asherszhang@tencent.com>
```
  5a7fb3ab
- [Kernel] DeepGemm MoE : Integrate triton permute / unpermute kernels (#20903) · 11dfdf21
  Varun Sundar Rabindranath authored Jul 17, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  11dfdf21
- [Misc] Fix PhiMoE expert mapping (#21085) · c5b8b595
  Jee Jee Li authored Jul 17, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  c5b8b595
- [Bugfix] Fix Machete zero point issue for GPTQ models on SM90 (#21066) · 28a6d542
  Michael Goin authored Jul 16, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  28a6d542
- [Bugfix] weight loading use correct tp_group with patch_tensor_parallel_group (#21024) · c9ba8104
  Kevin_Xiong authored Jul 17, 2025
```
Signed-off-by: KevinXiong-C <kevin_xiong1997@outlook.com>
```
  c9ba8104
16 Jul, 2025 11 commits
- Support FP8 Quantization and Inference Run on Intel Gaudi (HPU) using INC... · 01513a33
  Nir David authored Jul 16, 2025
```
Support FP8 Quantization and Inference Run on Intel Gaudi (HPU) using INC (Intel Neural Compressor) (#12010)
Signed-off-by: Nir David <ndavid@habana.ai>
Signed-off-by: Uri Livne <ulivne@habana.ai>
Co-authored-by: Uri Livne <ulivne@habana.ai>
```
  01513a33
- [Model] Remove model sampler (#21059) · ac2bf41e
  Cyrus Leung authored Jul 17, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ac2bf41e
- [fix] fix qwen image_embeds input (#21049) · a0f8a796
  Avshalom Manevich authored Jul 16, 2025
```
Signed-off-by: h-avsha <avshalom.manevich@hcompany.ai>
```
  a0f8a796
- [Model] Consolidate pooler implementations (#20927) · 1c3198b6
  Cyrus Leung authored Jul 16, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  1c3198b6
- [Meta] Llama4 EAGLE Support (#20591) · c11013db
  zhiweiz authored Jul 15, 2025
```
Signed-off-by: qizixi <qizixi@meta.com>
Co-authored-by: qizixi <qizixi@meta.com>
```
  c11013db
- [CI] update typos config for CI pre-commit and fix some spells (#20919) · 1eb2b9c1
  Peter Pan authored Jul 16, 2025
```
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
```
  1eb2b9c1
- [Doc] Remove duplicate docstring (#21012) · 76ddeff2
  Wentao Ye authored Jul 15, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  76ddeff2
- [Bugfix] Fix Mistral3 support on SM100/SM120 (#20998) · f4609833
  Michael Goin authored Jul 15, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  f4609833
- [Bugfix] Correct per_act_token in CompressedTensorsW8A8Fp8MoECutlassM… (#20937) · fcb9f879
  Ming Yang authored Jul 15, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
  fcb9f879
- [Chore] Remove outdated transformers check (#20989) · 75a99b98
  Brayden Zhong authored Jul 15, 2025
```
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
  75a99b98
- [Model] Add ModelConfig class for GraniteMoeHybrid to override default... · 6cbc4d4b
  Thomas Parnell authored Jul 16, 2025
```
[Model] Add ModelConfig class for GraniteMoeHybrid to override default max_seq_len_to_capture (#20923)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  6cbc4d4b
15 Jul, 2025 7 commits
- [BugFix] fix 3 issues: (1) using metadata for causal-conv1d, (2) indexing... · f29fd8a7
  Tuan, Hoang-Trong authored Jul 15, 2025
```
[BugFix] fix 3 issues: (1) using metadata for causal-conv1d, (2) indexing overflow in v1 vLLM, and (3) init_states in v0 (#20838)
Signed-off-by: Tuan M. Hoang-Trong <tmhoangt@us.ibm.com>
Co-authored-by: Tuan M. Hoang-Trong <tmhoangt@us.ibm.com>
```
  f29fd8a7
- Voxtral (#20970) · e7e3e6d2
  Patrick von Platen authored Jul 15, 2025
```
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  e7e3e6d2
- [V1] [Hybrid] Refactor mamba state shape calculation; enable V1 via cli (#20840) · 3534c39a
  Thomas Parnell authored Jul 15, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  3534c39a
- [Model] Add AutoWeightsLoader support for BERT, RoBERTa (#20534) · 85bd6599
  Jennifer He authored Jul 15, 2025
```
Signed-off-by: Jennifer He <islandhe@gmail.com>
Signed-off-by: <islandhe@gmail.com>
Signed-off-by: Jen H <islandhe@gmail.com>
```
  85bd6599
- Enabled BnB NF4 inference on Gaudi (#20172) · 016b8d1b
  Ruheena Suhani Shaik authored Jul 15, 2025
```
Signed-off-by: Ruheena Suhani Shaik <rsshaik@habana.ai>
```
  016b8d1b
- Use w8a8 quantized matmul Pallas kernel (#19170) · d4170fad
  XiongfeiWei authored Jul 14, 2025
```
Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
```
  d4170fad
- [Bugfix] Fix incorrect dispatch for CutlassBlockScaledGroupedGemm and DeepGEMM (#20933) · bcdfb2a3
  Michael Goin authored Jul 15, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  bcdfb2a3
14 Jul, 2025 4 commits
- Fix overflow indexing in causal_conv1d kernel (#20938) · 86f3ac21
  Thomas Parnell authored Jul 14, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  86f3ac21
- [Misc] ModularKernel : Perform WeightAndReduce inside TritonExperts & DeepGemmExperts (#20725) · c0569dbc
  Varun Sundar Rabindranath authored Jul 15, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  c0569dbc
- [Model] Add Ling implementation (#20680) · 38efa282
  ant-yy authored Jul 14, 2025
```
Signed-off-by: vito.yy <vito.yy@antgroup.com>
```
  38efa282
- [Quantization] add BNB for MixtralForCausalLM (#20893) · a99b9f7d
  Jee Jee Li authored Jul 14, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  a99b9f7d