Commits · a023edfa5bc1982ba5c6365ea2e36c6dfc48a9ef · OpenDAS / vllm_cscc

"examples/openai_embedding_client.py" did not exist on "4298374265a4379a2bd378373c7252b7a7b2b34f"

20 Apr, 2026 16 commits
- [bugfix] Use only onlines CPUs in lscpu (#40161) · a023edfa
  Galigator authored Apr 20, 2026
```
Signed-off-by: kse <kevin.sejourne@cloud-temple.com>
Co-authored-by: kse <kevin.sejourne@cloud-temple.com>
```
  a023edfa
- [Anthropic][Frontend] Added chat_template_kwargs to /v1/messages (#40125) · b82fc136
  aleksandaryanakiev authored Apr 20, 2026
```
Signed-off-by: Aleksandar Yanakiev <alexander.yanakiev@discretestack.com>
Co-authored-by: Aleksandar Yanakiev <alexander.yanakiev@discretestack.com>
```
  b82fc136
- nixl refactor [2/N]: unify TpKVTopology + HeteroTPTransferConfig into TransferTopology (#39529) · cc3993b0
  zhanqiuhu authored Apr 20, 2026
```
Signed-off-by: Zhanqiu Hu <zhu@redhat.com>
```
  cc3993b0
- [EPLB] Add nixl-based eplb communicator (#36276) · 50dd4cb4
  Ilya Markov authored Apr 20, 2026
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Markov Ilya <markovilya19@gmail.com>
```
  50dd4cb4
- [kv_offload+HMA][4/N]: Support sliding window lookup (#36645) · f774ba02
  Or Ozeri authored Apr 20, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
```
  f774ba02
- [CPU][BugFix] Fix inter-node pipeline parallel (#40150) · 2aab9acf
  Fadi Arafeh authored Apr 20, 2026
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
  2aab9acf
- [Bugfix] Fix scaled_mm output narrowing for 3D input tensors (#38093) · 58631d7c
  nemanjaudovic authored Apr 20, 2026
```
Signed-off-by: nemanjaudovic <nudovic@amd.com>
```
  58631d7c
- [Bugfix] Forward mm_processor_kwargs in offline generate APIs (#40251) · 77fd2c86
  wuyingjun authored Apr 20, 2026
```
Signed-off-by: wuyingjun <wuyingjun_yewu@cmss.chinamobile.com>
```
  77fd2c86
- [Fix] Add Spacing when Requesting Output Token > max_model_len (#40324) · e729cc82
  San-Nguyen authored Apr 20, 2026
```
Signed-off-by: San-Nguyen <san.nguyen@ibm.com>
```
  e729cc82
- [BUGFIX] Fix Pixtral consolidated format vision weight loading (#39916) · 6097afb9
  Julien Denize authored Apr 20, 2026
```
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
  6097afb9
- [XPU] [torch.compile] Skipping CUDA graph memory estimation to avoid startup errors. (#39977) · 4f4713f9
  Chaojun Zhang authored Apr 20, 2026
```
Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  4f4713f9
- [Qwen][Bugfix] Fixes sigmoid activation in torch impl of RMSNormGated. (#40245) · 89361181
  Tao He authored Apr 20, 2026
```
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
```
  89361181
- fix: Do not make function calls when request has no tools for /v1/responses (#40314) · 67ed01c3
  Yuan Tang authored Apr 20, 2026
```
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
```
  67ed01c3
- [Bugfix][Responses API] Fix streaming tool calls on /v1/responses (#39892) · 6e10cb54
  Hoang Nguyen authored Apr 20, 2026
```
Signed-off-by: Hoang Nguyen <118159510+hnt2601@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
```
  6e10cb54
- [Bugfix] Properly initialize `PerTensorScaleParameter` for fused-on-disk checkpoints (#39765) · fcb31c1a
  Shinichi Hemmi authored Apr 20, 2026
```
Signed-off-by: Hemmi Shinichi <shemmi@preferred.jp>
Signed-off-by: Shinichi Hemmi <50256998+Alnusjaponica@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  fcb31c1a
- [BugFix][XPU] fix lora ops bgmv_expand size not match (#39989) · 898beca5
  Liangliang Ma authored Apr 20, 2026
```
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  898beca5
19 Apr, 2026 7 commits
- [ROCm] Fix cu_seqlens_q off-by-one in AITER FA speculative decode path (#39120) · f150107e
  Andrew Barnes authored Apr 19, 2026
```
Signed-off-by: Bortlesboat <bortstheboat@gmail.com>
```
  f150107e
- Fix MoE backend selection for LoRA (unquantized MoE) (#40273) · d1135a50
  danisereb authored Apr 19, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
  d1135a50
- Optimize nemotron VL image/video preprocessing (#40283) · 982beae8
  Netanel Haber authored Apr 19, 2026
```
Signed-off-by: milesial <milesial@users.noreply.github.com>
Co-authored-by: milesial <milesial@users.noreply.github.com>
```
  982beae8
- [FEAT] [Perf] [Gemma4] Fused Gemma4 Routing Function Triton (#39083) · 45232a45
  TJian authored Apr 19, 2026
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  45232a45
- [Bugfix] Kimi-K2 tool parser streaming - fix token leakage, argument... · 03ce1c6e
  Flora Feng authored Apr 19, 2026
```
[Bugfix] Kimi-K2 tool parser streaming - fix token leakage, argument truncation, and content dropping (#38579)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
```
  03ce1c6e
- [KV Offload] Pass request context (#39185) · 4353c9cb
  omerpaz95 authored Apr 19, 2026
```
Signed-off-by: omerpaz95 <omerpaz95@gmail.com>
```
  4353c9cb
- [KV Connector] Allow metrics of multiple connectors of same types in multi connector. (#40010) · 4b7f5ea1
  omerpaz95 authored Apr 19, 2026
```
Signed-off-by: omerpaz95 <omerpaz95@gmail.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
```
  4b7f5ea1
18 Apr, 2026 11 commits
- [Frontend] Preserve structured output special tokens in offline LLM.chat (#39352) · 38907e43
  Luciano Martins authored Apr 18, 2026
```
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
```
  38907e43
- [Attention] TurboQuant: remove redundant random signs, add prior art attribution (#40194) · ed0622e3
  Dan Alistarh authored Apr 18, 2026
```
Signed-off-by: Dan Alistarh <d.alistarh@gmail.com>
```
  ed0622e3
- Added general ND x ND matmul and unit test for it (#39909) · b5f6c5f8
  Yusuf Mohammad authored Apr 18, 2026
```
Signed-off-by: Yusuf <yusufmohammad@live.com>
```
  b5f6c5f8
- [Refactor] Drop direct dependency on librosa (#39079) · 153ba7f0
  Nick Cao authored Apr 18, 2026
```
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
```
  153ba7f0
- [ZenCPU] AMD Zen CPU Backend with supported dtypes via zentorch weekly (#39967) · 87518c30
  Chinmay-Kulkarni-AMD authored Apr 18, 2026
```
Signed-off-by: Chinmay Kulkarni <Chinmay.Kulkarni@amd.com>
```
  87518c30
- [Bugfix] Fix k_proj's bias for GLM-ASR (#40160) · aeee7ef9
  Rishapveer Singh authored Apr 18, 2026
```
Signed-off-by: Rishapveer Singh <singhrishapveer@gmail.com>
```
  aeee7ef9
- [Doc] Fix outdated source reference comment in anthropic/serving.py (#40189) · cda19ecf
  z1ying authored Apr 17, 2026
```
Signed-off-by: z1ying <tzzying@outlook.com>
```
  cda19ecf
- [Frontend] Add multimodal support to /inference/v1/generate endpoint (#38405) · 80b18230
  Nithin Chalapathi authored Apr 17, 2026
```
Signed-off-by: Nithin Chalapathi <nithin.ch10@gmail.com>
Signed-off-by: Nithin Chalapathi <nithinc@berkeley.edu>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  80b18230
- [Core] Reduce mm scheduler, get_num_embed overhead (#40143) · b0755523
  milesial authored Apr 17, 2026
```
Signed-off-by: milesial <milesial@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  b0755523
- [XPU] fix all_reduce all-zero accuracy issue under torch.compile (#39844) · 993859ce
  Chaojun Zhang authored Apr 18, 2026
```
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
```
  993859ce
- [XPU]fake impl for xpu fp8_gemm (#39984) · 55842a8d
  Xinyu Chen authored Apr 18, 2026
```
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  55842a8d
17 Apr, 2026 6 commits
- [Kernel] Add MXFP4 W4A4 CUTLASS MoE kernel for SM100 (#37463) · a8bffaa1
  Michael Goin authored Apr 17, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  a8bffaa1
- [Kernel] [Helion] Force disable HOP path due to performance regression (#40171) · 5cdddddd
  Yanan Cao authored Apr 17, 2026
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Sonnet 4 <noreply@anthropic.com>
```
  5cdddddd
- [ROCm] Fix TurboQuant on ROCm: backend routing, flash-attn compat, int64 overflow (#39953) · 6ef1efd5
  aditi-amd authored Apr 17, 2026
```
Signed-off-by: aditi <aditi.rana@amd.com>
```
  6ef1efd5
- skip fp8e4b15 on xpu (#39957) · 251c18d1
  Xinyu Chen authored Apr 18, 2026
```
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  251c18d1
- [Misc][UX] Map mimo reasoning and tooling parsers (#40089) · 512765d5
  Roger Wang authored Apr 17, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  512765d5
- feat: Add LoRA support for Gemma4ForConditionalGeneration (#39291) · 640cc9dd
  allgather authored Apr 17, 2026
```
Signed-off-by: allgather <all2allops@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
```
  640cc9dd