Commits · d719ba24c5b4e669bf51b49293cab09f2ce7361c · OpenDAS / vllm_cscc · GitLab

12 Jul, 2024 16 commits
- Build some nightly wheels by default (#6380) · d719ba24
  Simon Mo authored Jul 12, 2024
  
  d719ba24
- [MISC] Upgrade dependency to PyTorch 2.3.1 (#5327) · aa48e502
  Cody Yu authored Jul 12, 2024
  
  aa48e502
- [ci] Add GHA workflows to enable full CI run (#6381) · 4dbebd03
  Kevin H. Luu authored Jul 12, 2024
```
Signed-off-by: kevin <kevin@anyscale.com>
```
  4dbebd03
- [ci] Add grouped tests & mark tests to run by default for fastcheck pipeline (#6365) · b75bce10
  Kevin H. Luu authored Jul 12, 2024
```
Signed-off-by: kevin <kevin@anyscale.com>
```
  b75bce10
- [Misc] add fixture to guided processor tests (#6341) · b039cbbc
  Yihuan Bu authored Jul 12, 2024
  
  b039cbbc
- [Build/CI] Checking/Waiting for the GPU's clean state (#6379) · f9d25c25
  Alexei-V-Ivanov-AMD authored Jul 12, 2024
  
  f9d25c25
- [Bugfix] Fix dtype mismatch in PaliGemma (#6367) · 024ad87c
  Cyrus Leung authored Jul 12, 2024
  
  024ad87c
- [ Misc ] Support Models With Bias in `compressed-tensors` integration (#6356) · aea19f09
  Robert Shaw authored Jul 12, 2024
  
  aea19f09
- [Misc][Bugfix] Update transformers for tokenizer issue (#6364) · f7160d94
  Roger Wang authored Jul 12, 2024
  
  f7160d94
- [ Misc ] Remove separate bias add (#6353) · 6047187c
  Robert Shaw authored Jul 12, 2024
  
  6047187c
- [ROCm][AMD] unify CUDA_VISIBLE_DEVICES usage in cuda/rocm (#6352) · b6c16cf8
  Hongxia Yang authored Jul 12, 2024
  
  b6c16cf8
- [CI/Build] (2/2) Switching AMD CI to store images in Docker Hub (#6350) · d26a8b3f
  adityagoel14 authored Jul 12, 2024
  
  d26a8b3f
- [Model][Phi3-Small] Remove scipy from blocksparse_attention (#6343) · d59eb984
  Michael Goin authored Jul 11, 2024
  
  d59eb984
- [Bugfix] Fix usage stats logging exception warning with OpenVINO (#6349) · adf32e0a
  Helena Kloosterman authored Jul 12, 2024
  
  adf32e0a
- [distributed][misc] be consistent with pytorch for libcudart.so (#6346) · 2b0fb534
  youkaichao authored Jul 11, 2024
```
[distributed][misc] keep consistent with how pytorch finds libcudart.so (#6346)
```
  2b0fb534
- [Misc] Remove flashinfer warning, add flashinfer tests to CI (#6351) · d6ab5289
  Lily Liu authored Jul 11, 2024
  
  d6ab5289
11 Jul, 2024 14 commits
- [ BugFix ] Prompt Logprobs Detokenization (#6223) · 7ed6a4f0
  Robert Shaw authored Jul 11, 2024
```
Co-authored-by: Zifei Tong <zifeitong@gmail.com>
```
  7ed6a4f0
- [CI/Build] Add nightly benchmarking for tgi, tensorrt-llm and lmdeploy (#5362) · a4feba92
  Kuntai Du authored Jul 11, 2024
  
  a4feba92
- [doc] update pipeline parallel in readme (#6347) · 2d23b42d
  youkaichao authored Jul 11, 2024
  
  2d23b42d
- [bug fix] Fix llava next feature size calculation. (#6339) · 1df43de9
  xwjiang2010 authored Jul 11, 2024
```
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
```
  1df43de9
- Benchmark: add H100 suite (#6047) · 52b7fcb3
  Simon Mo authored Jul 11, 2024
  
  52b7fcb3
- [ Misc ] Refactor Marlin Python Utilities (#6082) · b675069d
  Robert Shaw authored Jul 11, 2024
```
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
```
  b675069d
- [BugFix] get_and_reset only when scheduler outputs are not empty (#6266) · 55f692b4
  Mor Zusman authored Jul 11, 2024
  
  55f692b4
- [Bugfix] GPTBigCodeForCausalLM: Remove lm_head from supported_lora_modules. (#6326) · 8a1415cf
  Thomas Parnell authored Jul 11, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Travis Johnson <tsjohnso@us.ibm.com>
```
  8a1415cf
- [BugFix]: fix engine timeout due to request abort (#6255) · 546b101f
  pushan authored Jul 11, 2024
```
Signed-off-by: yatta zhang <ytzhang01@foxmail.com>
Signed-off-by: zhangyuntao.dev <zhangyuntao.dev@bytedance.com>
Co-authored-by: zhangyuntao.dev <zhangyuntao.dev@bytedance.com>
```
  546b101f
- [Misc] refactor(config): clean up unused code (#6320) · 3963a533
  aniaan authored Jul 11, 2024
  
  3963a533
- [Bugfix] Fix snapshot download in serving benchmark (#6318) · c4774eb8
  Roger Wang authored Jul 11, 2024
  
  c4774eb8
- [BugFix]: set outlines pkg version (#6262) · fc17110b
  Lim Xiang Yang authored Jul 11, 2024
  
  fc17110b
- [Doc] Update description of vLLM support for CPUs (#6003) · 439c8458
  Jie Fu (傅杰) authored Jul 11, 2024
  
  439c8458
- [Doc] Remove comments incorrectly copied from another project (#6286) · 99ded1e1
  daquexian authored Jul 11, 2024
  
  99ded1e1
10 Jul, 2024 10 commits
- [Bugfix][Neuron] Fix soft prompt method error in NeuronExecutor (#6313) · 997df46a
  Woosuk Kwon authored Jul 10, 2024
  
  997df46a
- [Speculative Decoding] Enabling bonus token in speculative decoding for KV... · ae151d73
  sroy745 authored Jul 10, 2024
```
[Speculative Decoding] Enabling bonus token in speculative decoding for KV cache based models (#5765)
```
  ae151d73
- [Bugfix] Fix OpenVINOExecutor abstractmethod error (#6296) · 44cc7661
  sangjune.park authored Jul 11, 2024
```
Signed-off-by: sangjune.park <sangjune.park@navercorp.com>
```
  44cc7661
- [CI/Build] Enable mypy typing for remaining folders (#6268) · b422d496
  Benjamin Muskalla authored Jul 10, 2024
  
  b422d496
- [Bugfix] MLPSpeculator: Use ParallelLMHead in tie_weights=False case. (#6303) · c38eba30
  Thomas Parnell authored Jul 10, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  c38eba30
- [Bugfix] Support 2D input shape in MoE layer (#6287) · e72ae80b
  Woosuk Kwon authored Jul 10, 2024
  
  e72ae80b
- [Doc] Guide for adding multi-modal plugins (#6205) · 8a924d22
  Cyrus Leung authored Jul 10, 2024
  
  8a924d22
- [Bugfix][TPU] Add prompt adapter methods to TPUExecutor (#6279) · 5ed3505d
  Woosuk Kwon authored Jul 09, 2024
  
  5ed3505d
- [core][distributed] zmq fallback for broadcasting large objects (#6183) · da78caec
  youkaichao authored Jul 09, 2024
```
[core][distributed] add zmq fallback for broadcasting large objects (#6183)
```
  da78caec
- [Speculative Decoding] Medusa Implementation with Top-1 proposer (#4978) · 2416b26e
  Abhinav Goyal authored Jul 10, 2024
  
  2416b26e