Commits · 8af5a5c4e580ee20674dfe8be8cd687677419d8c · OpenDAS / vllm_cscc · GitLab

01 Apr, 2025 4 commits
- [V1] Implement sliding window attention in kv_cache_manager (#14097) · 3a5f0afc
  Chen Zhang authored Apr 01, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  3a5f0afc
- [Bugfix][Model] fix mllama multi-image (#14883) · ff647398
  Yan Ma authored Apr 01, 2025
```
Signed-off-by: yan ma <yan.ma@intel.com>
```
  ff647398
- Rename fallback model and refactor supported models section (#15829) · a76f547e
  Harry Mellor authored Apr 01, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  a76f547e
- [Distributed] Add custom allreduce support for ROCM (#14125) · b7b7676d
  Ilya Markov authored Apr 01, 2025
```
Signed-off-by: ilmarkov <imarkov@redhat.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
```
  b7b7676d
31 Mar, 2025 9 commits
- [V1][Core] Remove unused speculative config from scheduler (#15818) · f98a4920
  Mark McLoughlin authored Mar 31, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  f98a4920
- [V1] TPU CI - Add basic perf regression test (#15414) · 9a2160fa
  Alexander Matveev authored Mar 31, 2025
```
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
```
  9a2160fa
- [V1][Spec Decode] Remove deprecated spec decode config params (#15466) · 239b7bef
  shangmingc authored Apr 01, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  239b7bef
- [Bugfix] Check dimensions of multimodal embeddings in V1 (#15816) · 09e974d4
  Cyrus Leung authored Apr 01, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  09e974d4
- Upgrade `transformers` to `v4.50.3` (#13905) · e5ef4fa9
  Harry Mellor authored Mar 31, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  e5ef4fa9
- [Bugfix] Fix Crashing When Loading Modules With Batchnorm Stats (#15813) · c2e7507a
  Alex Brooks authored Mar 31, 2025
```
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
```
  c2e7507a
- [Model] Update support for NemotronNAS models (#15008) · 3aa2b6a6
  Naveassaf authored Mar 31, 2025
```
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
```
  3aa2b6a6
- [V1] Fully Transparent Implementation of CPU Offloading (#15354) · 555aa219
  youkaichao authored Mar 31, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  555aa219
- [Feature][ROCm]Enable fusion pass for torch.compile on ROCm (#15050) · e8582945
  Charlie Fu authored Mar 31, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  e8582945
30 Mar, 2025 5 commits
- fix: lint fix a ruff checkout syntax error (#15767) · 248e76c4
  yihong authored Mar 30, 2025
```
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
```
  248e76c4
- [V1] Override `mm_counts` for dummy data creation (#15703) · 803d5c35
  Cyrus Leung authored Mar 30, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  803d5c35
- fix test_phi3v (#15321) · 7fd8c0f8
  pansicheng authored Mar 30, 2025
```
Signed-off-by: pansicheng <sicheng.pan.chn@gmail.com>
```
  7fd8c0f8
- [Bugfix] Fix Mistral guided generation using xgrammar (#15704) · 6909a762
  Julien Denize authored Mar 30, 2025
```
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
```
  6909a762
- [CI] xgrammar structured output supports Enum. (#15757) · 04553371
  Chauncey authored Mar 30, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  04553371
29 Mar, 2025 5 commits
- [V1] Support interleaved modality items (#15605) · c67abd61
  Roger Wang authored Mar 29, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  c67abd61
- [FEAT] [ROCm] Add AITER int8 scaled gemm kernel (#15433) · 4965ec42
  TJian authored Mar 29, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  4965ec42
- [CI] Speed up V1 structured output tests (#15718) · 7a799208
  Russell Bryant authored Mar 29, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  7a799208
- [Bugfix] LoRA V1: add and fix entrypoints tests (#15715) · 1286211f
  Varun Sundar Rabindranath authored Mar 28, 2025
```
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
```
  1286211f
- [Model] Support Skywork-R1V (#15397) · de1cb387
  pengyuange authored Mar 29, 2025
```
Signed-off-by: jiacai.liu <932997367@qq.com>
Co-authored-by: jiacai.liu <932997367@qq.com>
```
  de1cb387
28 Mar, 2025 13 commits
- [V1] TPU - Fix the chunked prompt bug (#15713) · c3f687ac
  Alexander Matveev authored Mar 28, 2025
```
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
```
  c3f687ac
- [Bugfix] [torch.compile] Add Dynamo metrics context during compilation (#15639) · 04437e31
  Luka Govedič authored Mar 28, 2025
```
Signed-off-by: luka <luka@neuralmagic.com>
```
  04437e31
- [Misc] Remove unused utils and clean up imports (#15708) · c6bc0034
  Cyrus Leung authored Mar 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c6bc0034
- Fix cpu offload testing for gptq/awq/ct (#15648) · 47e9038d
  Michael Goin authored Mar 28, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  47e9038d
- [V1] Support disable_any_whtespace for guidance backend (#15584) · 7329ff54
  Russell Bryant authored Mar 28, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  7329ff54
- [Bugfix][v1] xgrammar structured output supports Enum. (#15594) · 3b00ff91
  Chauncey authored Mar 28, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  3b00ff91
- [Bugfix][Frontend] Eliminate regex based check in reasoning full generator (#14821) · 3bbaacbe
  Ce Gao authored Mar 28, 2025
```
Signed-off-by: Ce Gao <cegao@tensorchord.ai>
```
  3bbaacbe
- [Misc] Fix test_sleep to use query parameters (#14373) · a10314c6
  Lize Cai authored Mar 28, 2025
```
Signed-off-by: Lize Cai <lize.cai@sap.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  a10314c6
- [Refactor][Frontend] Keep all logic about reasoning into one class (#14428) · 32b14baf
  Ce Gao authored Mar 28, 2025
```
Signed-off-by: Ce Gao <cegao@tensorchord.ai>
```
  32b14baf
- [TPU][CI] Fix TPUModelRunner Test (#15667) · 2d9045fc
  Robert Shaw authored Mar 28, 2025
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  2d9045fc
- [V1] Remove legacy input registry (#15673) · 355f6634
  Cyrus Leung authored Mar 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  355f6634
- [CI][TPU] Temporarily Disable Quant Test on TPU (#15649) · 8a49eea7
  Robert Shaw authored Mar 27, 2025
```
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
```
  8a49eea7
- [Quantization][V1] BitsAndBytes support V1 (#15611) · 726efc6a
  Jee Jee Li authored Mar 28, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  726efc6a
27 Mar, 2025 4 commits
- [V1] AsyncLLM data parallel (#13923) · 15dac210
  Nick Hill authored Mar 27, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  15dac210
- [Bugfix][TPU][V1] Fix recompilation (#15553) · 4098b722
  Nicolò Lucchesi authored Mar 27, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  4098b722
- [Misc] Replace `is_encoder_decoder_inputs` with `split_enc_dec_inputs` (#15620) · 24718153
  Cyrus Leung authored Mar 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  24718153
- [V1] Refactor num_computed_tokens logic (#15307) · 54aa6194
  Cody Yu authored Mar 26, 2025
```
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  54aa6194