Commits · 98d7367b614bf4bb2189e849723df24156de67d0 · OpenDAS / vllm_cscc · GitLab

02 Apr, 2025 20 commits
- [Metrics] Hide deprecated metrics (#15458) · 98d7367b
  Mark McLoughlin authored Apr 02, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  98d7367b
- [Bugfix] Fix the issue where the model name is empty string, causing no... · 594a8b90
  Chauncey authored Apr 02, 2025
```
[Bugfix] Fix the issue where the model name is empty string, causing no response with the model name. (#15938)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  594a8b90
- [CI] Remove duplicate entrypoints-test (#15940) · 44f99051
  Kay Yan authored Apr 02, 2025
```
Signed-off-by: Kay Yan <kay.yan@daocloud.io>
```
  44f99051
- [Bugfix][Benchmarks] Ensure `async_request_deepspeed_mii` uses the OpenAI choices key (#15926) · 25293780
  Brayden Zhong authored Apr 02, 2025
```
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
  25293780
- Add minimum version for `huggingface_hub` to enable Xet downloads (#15873) · 51826d51
  Harry Mellor authored Apr 02, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  51826d51
- [V1] Fix json_object support with xgrammar (#15488) · 14e53ed1
  Russell Bryant authored Apr 02, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  14e53ed1
- [core] Add tags parameter to wake_up() (#15500) · ddb94c26
  Eric Tang authored Apr 02, 2025
```
Signed-off-by: Eric <erictang000@gmail.com>
```
  ddb94c26
- [Kernel] Add more dtype support for GGUF dequantization (#15879) · 90969fb3
  LukasBluebaum authored Apr 02, 2025
```
Signed-off-by: lukas.bluebaum <lukas.bluebaum@aleph-alpha.com>
```
  90969fb3
- [Build/CI] Update lm-eval to 0.4.8 (#15912) · 101f1481
  Chris Thi authored Apr 02, 2025
```
Signed-off-by: Chris Thi <chris.c.thi@gmail.com>
```
  101f1481
- [Bugfix] Fix cache block size calculation for CPU MLA (#15848) · 2edc87b1
  Thien Tran authored Apr 02, 2025
```
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
```
  2edc87b1
- [CI/Build] Further clean up LoRA tests (#15920) · 4203926f
  Jee Jee Li authored Apr 02, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  4203926f
- [Misc] Replace print with logger (#15923) · cdb57015
  Chauncey authored Apr 02, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  cdb57015
- [Benchmark]Fix error message (#15866) · aa557e64
  Li Wang authored Apr 02, 2025
```
Signed-off-by: wangli <wangli858794774@gmail.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
```
  aa557e64
- [V1][Bugfix] Fix typo in MoE TPU checking (#15927) · 0e00d40e
  Roger Wang authored Apr 01, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  0e00d40e
- [Doc] Update rocm.inc.md (#15917) · c920e012
  chun authored Apr 02, 2025
```
Signed-off-by: chun37 <chun.jb.37@gmail.com>
```
  c920e012
- [V1][Minor] Enhance SpecDecoding Metrics Log in V1 (#15902) · 274d8e88
  Woosuk Kwon authored Apr 01, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  274d8e88
- [Bugfix] Fix imports for MoE on CPU (#15841) · 2039c630
  Thien Tran authored Apr 02, 2025
```
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
```
  2039c630
- [V1] Fix: make sure `k_index` is int64 for `apply_top_k_only` (#15907) · 6efb195a
  Brayden Zhong authored Apr 01, 2025
```
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
  6efb195a
- [Spec Decode] Fix input triton kernel for eagle (#15909) · 24b7fb45
  Ekagra Ranjan authored Apr 01, 2025
  
  24b7fb45
- [Docs] Add Intel as Sponsor (#15913) · 58f5a597
  Simon Mo authored Apr 01, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  58f5a597
01 Apr, 2025 20 commits
- [Docs] Add Ollama meetup slides (#15905) · db9dfcfa
  Simon Mo authored Apr 01, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  db9dfcfa
- [Model][MiniMaxText01] Support MiniMaxText01 model inference (#13454) · 9ef98d52
  Gerald authored Apr 02, 2025
```
Signed-off-by: qscqesze <475517977@qq.com>
Co-authored-by: qingjun <qingjun@minimaxi.com>
Co-authored-by: qscqesze <475517977@qq.com>
```
  9ef98d52
- [BugFix] make sure socket close (#15875) · 93491aef
  yihong authored Apr 02, 2025
```
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
```
  93491aef
- [Docs] update usage stats language (#15898) · 7acd539c
  Simon Mo authored Apr 01, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  7acd539c
- [V1][Spec Decode] Implement Eagle Proposer [1/N] (#15729) · e75a6301
  Woosuk Kwon authored Apr 01, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  e75a6301
- [V1][Metrics] Initial speculative decoding metrics (#15151) · a79cc68b
  Mark McLoughlin authored Apr 01, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  a79cc68b
- [CI] Disable flaky structure decoding test temporarily. (#15892) · 7e3f7a4e
  Roger Wang authored Apr 01, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  7e3f7a4e
- [Model] Add module name prefixes to gemma3 (#15889) · 9ec82579
  cloud11665 authored Apr 02, 2025
```
Signed-off-by: Bartholomew Sabat <bartek@recursal.ai>
Co-authored-by: Bartholomew Sabat <bartek@recursal.ai>
```
  9ec82579
- [Model] Aya Vision (#15441) · 38327cf4
  Jennifer Zhao authored Apr 01, 2025
```
Signed-off-by: Jennifer Zhao <ai.jenniferzhao@gmail.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  38327cf4
- [CI/Build] Clean up LoRA tests (#15867) · dfa82e2a
  Jee Jee Li authored Apr 02, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  dfa82e2a
- Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. (#13932) · e59ca942
  bnellnm authored Apr 01, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  e59ca942
- [ROCm][Build][Bugfix] Bring the base dockerfile in sync with the ROCm fork (#15820) · a57a3044
  Gregory Shtrasberg authored Apr 01, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  a57a3044
- [Misc] Allow using OpenCV as video IO fallback (#15055) · 4e5a0f6a
  Isotr0py authored Apr 01, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  4e5a0f6a
- Reinstate `format.sh` and make `pre-commit` installation simpler (#15890) · b63bd149
  Harry Mellor authored Apr 01, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  b63bd149
- [Doc] Quark quantization documentation (#15861) · 2041c0e3
  chaow-amd authored Apr 01, 2025
```
Signed-off-by: chaow <chaow@amd.com>
```
  2041c0e3
- [New Model]: jinaai/jina-reranker-v2-base-multilingual (#15876) · 085cbc4f
  wang.yuqi authored Apr 01, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  085cbc4f
- Remove `format.sh` as it's been unsupported >70 days (#15884) · 2b93162f
  Harry Mellor authored Apr 01, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2b93162f
- [Misc] remove unused script (#15746) · 2e45bd29
  Reid authored Apr 01, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  2e45bd29
- [Model] Support Mistral3 in the HF Transformers format (#15505) · 51d7c6a2
  Michael Goin authored Apr 01, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  51d7c6a2
- setup correct nvcc version with CUDA_HOME (#15725) · f3aca1ee
  Yang Chen authored Apr 01, 2025
```
Signed-off-by: Yang Chen <yangche@fb.com>
```
  f3aca1ee