Commits · 44eef0ca1ece551e5ee40e099f6f9bb67fc5733c · OpenDAS / vllm_cscc · GitLab

31 Mar, 2026 1 commit
- vLLM Benchmark Suite perf regression after PR#32723 (#38576) · 44eef0ca
  Louie Tsai authored Mar 30, 2026
```
Signed-off-by: louie-tsai <louie.tsai@intel.com>
```
  44eef0ca
30 Mar, 2026 3 commits
- [Bugfix][CPU] Skip set_num_threads after thread binding (#38535) · 6557f493
  Li, Jiang authored Mar 30, 2026
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  6557f493
- [ci] Soft fail and disable retry for AMD build image job (#38505) · fec5aeca
  Kevin H. Luu authored Mar 29, 2026
```
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
```
  fec5aeca
- [ROCm][CI] Enable hybrid chunked prefill test (#38317) · 4f2ed5fd
  Andreas Karatzas authored Mar 29, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  4f2ed5fd
29 Mar, 2026 1 commit
- [QeRL] Fix online quantized reloading (#38442) · d28d86e8
  Kyle Sayers authored Mar 29, 2026
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  d28d86e8
28 Mar, 2026 1 commit
- [ROCm] [Release] Update ROCm variant from rocm700 to rocm721 (#38413) · 58a249bc
  TJian authored Mar 28, 2026
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  58a249bc
27 Mar, 2026 3 commits

[EPLB] Cleanup the transfer logic for the various eplb maps (#34520) · 497e234d
Sage Moore authored Mar 27, 2026
```
Signed-off-by: Sage Moore <sagmoore@redhat.com>
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
497e234d

[CI/Build] Move nightly wheel index generation to a single post-build step (#38322) · 84e439a9

Shengqi Chen authored Mar 27, 2026

Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

84e439a9

[CI/Build] enable Intel XPU test flow with prebuilt image (#37447) · d8606012
wenjun liu authored Mar 27, 2026
```
Signed-off-by: wendyliu235 <wenjun.liu@intel.com>
```
d8606012

26 Mar, 2026 7 commits
- [Model Runner V2] Enable forcing a specific acceptance rate during rejection sampling (#38045) · c32e9760
  Giancarlo Delfin authored Mar 26, 2026
```
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
```
  c32e9760
- [ROCm] [Bugfix] [Release] Fix nightly rocm release pipeline (#38263) · bc9c6fbb
  TJian authored Mar 27, 2026
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  bc9c6fbb
- [ROCm][CI] Override PYTORCH_ROCM_ARCH with detected GPU arch in test containers (#38165) · bff9a1c2
  Andreas Karatzas authored Mar 26, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  bff9a1c2
- [ROCm][CI] Add LM Eval Qwen3.5 Models test for MI355 (#38155) · 9c3ae04b
  Andreas Karatzas authored Mar 26, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  9c3ae04b
- [Releases] [ROCm] Enable Nightly Docker Image and Wheel Releases for ROCm (#37283) · 60af7b96
  TJian authored Mar 27, 2026
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Hongxia Yang <hongxiay.yang@amd.com>
```
  60af7b96
- [CI] Add batch invariant test for b200 (#38014) · e054f152
  Wentao Ye authored Mar 26, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  e054f152
- [cpu][ci] remove soft-fail for Arm CI and add quant model tests (#37691) · 71161e8b
  Fadi Arafeh authored Mar 26, 2026
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
  71161e8b
25 Mar, 2026 4 commits
- [compile] Add some more startup tests for top models (#38046) · 6e37c46b
  Richard Zou authored Mar 25, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  6e37c46b
- [ROCm][CI] Rename filepath test to point to correct file (#38102) · 04417ecd
  Andreas Karatzas authored Mar 25, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  04417ecd
- [ROCm] Attention selector reordering (#36702) · 189ddefb
  Gregory Shtrasberg authored Mar 25, 2026
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
```
  189ddefb
- [Bugfix][ROCm][MoE] Fix mxfp4 oracle regressions from #37128 (#37787) · 679c6a3e
  Andreas Karatzas authored Mar 24, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  679c6a3e
24 Mar, 2026 9 commits
- [ROCm][CI][PD] Add Hybrid SSM integration tests to CI (#37924) · 8bbb7c7f
  Andreas Karatzas authored Mar 24, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  8bbb7c7f
- [release] Move the rest of release jobs to release queue (#38044) · af945615
  Kevin H. Luu authored Mar 24, 2026
```
Signed-off-by: khluu <khluu000@gmail.com>
```
  af945615
- Add Ubuntu 24.04 support for Docker builds (#35386) · 0c1809c8
  amey asgaonkar authored Mar 24, 2026
```
Signed-off-by: aasgaonkar <aasgaonkar@nvidia.com>
```
  0c1809c8
- [Bugfix] Add replacement of _compute_slot_mapping_kernel on CPU (#37987) · 352b90c4
  Li, Jiang authored Mar 24, 2026
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  352b90c4
- [release] Move agent queue to Release cluster queues (#37783) · 7281199a
  Kevin H. Luu authored Mar 23, 2026
```
Signed-off-by: khluu <khluu000@gmail.com>
```
  7281199a
- Downsize CPU jobs to use small queue (#37913) · b2dd75eb
  Kevin H. Luu authored Mar 23, 2026
```
Signed-off-by: khluu <khluu000@gmail.com>
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
```
  b2dd75eb
- [ROCm][CI] Split Entrypoints Integration (API Server 1) into 3 jobs (#37906) · de99d91e
  Andreas Karatzas authored Mar 23, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  de99d91e
- [CI] Add batch invariant test: Block FP8 + small MOE (#37895) · 83c9d525
  Wentao Ye authored Mar 23, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  83c9d525
- [Test] E2E Nemotron-3-Super tests (#36803) · 56777b5c
  roikoren755 authored Mar 24, 2026
```
Signed-off-by: Roi Koren <roik@nvidia.com>
```
  56777b5c
23 Mar, 2026 5 commits
- [CI] Split V1 Others into 3 separate jobs (#37016) · 2488a82f
  Kevin H. Luu authored Mar 23, 2026
```
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  2488a82f
- [Sparse24] [Deprecation] Remove Sparse24 CT integration and kernels (#36799) · 38364a7e
  Kyle Sayers authored Mar 23, 2026
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  38364a7e
- [CI] split Entrypoints Integration (API Server 1) into 3 jobs (#37882) · 91fd695b
  Kunshang Ji authored Mar 24, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  91fd695b
- [CI][PD] Add Hybrid SSM integration tests to CI (#37657) · 1cbbcfe8
  Nicolò Lucchesi authored Mar 23, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  1cbbcfe8
- [CI/Build][LoRA] Update Qwen35 LoRA testing (#37816) · 1f0d2106
  Jee Jee Li authored Mar 23, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  1f0d2106
22 Mar, 2026 3 commits
- [MRV2] Enable PP CUDA graph test (#37830) · 43877a62
  Woosuk Kwon authored Mar 22, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  43877a62
- [ROCm][CI] Make some duplicated tests optional so that they are only evaluated... · 6eedec6e
  Andreas Karatzas authored Mar 22, 2026
```
[ROCm][CI] Make some duplicated tests optional so that they are only evaluated in our nightly (#37780)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  6eedec6e
- [ROCm][CI] close missing quote in kernels/moe block in run-amd-test.sh (#37774) · e78bc742
  Andreas Karatzas authored Mar 21, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  e78bc742
21 Mar, 2026 3 commits
- [Quantization][Deprecation] Remove PTPC FP8 (#32700) · eeee5b26
  Robert Shaw authored Mar 21, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  eeee5b26
- [ROCm][CI] Update GSM8K eval config to use fp8-and-mixed models list (MI355) (#37721) · 02eec7ec
  Andreas Karatzas authored Mar 21, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  02eec7ec
- [ROCm][CI] Mark gemma3 as large GPU test to avoid OOM on MI250 (#37610) · 0d50fa1d
  Andreas Karatzas authored Mar 20, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  0d50fa1d