Commits · 55588cbd53b9c5903bfd62be3d00edbab3f5421d · OpenDAS / vllm_cscc

29 Aug, 2024 1 commit
- add torch version · 55588cbd
  zhuwenwen authored Aug 29, 2024
  
  55588cbd
16 Aug, 2024 1 commit
- update version · 0451580f
  zhuwenwen authored Aug 16, 2024
  
  0451580f
13 Aug, 2024 1 commit
- fix build error · d1787c31
  zhuwenwen authored Aug 13, 2024
  
  d1787c31
09 Aug, 2024 1 commit
- 增添lmslim gptq支持 · dcaabcf7
  gaoqiong authored Aug 09, 2024
  
  dcaabcf7
08 Aug, 2024 1 commit
- add git version for internal testing · 52c3dd59
  zhuwenwen authored Aug 08, 2024
  
  52c3dd59
06 Aug, 2024 2 commits
- update version and add gptq_kernels info · c7e7ca7b
  zhuwenwen authored Aug 06, 2024
  
  c7e7ca7b
- update version and skip install gptq_kernels · 58fb0c33
  zhuwenwen authored Aug 06, 2024
  
  58fb0c33
02 Aug, 2024 2 commits
- [Misc] Disambiguate quantized types via a new ScalarType (#6396) · a8d604ca
  Lucas Wilkinson authored Aug 02, 2024
  
  a8d604ca
- [CI/Build] Add support for Python 3.12 (#7035) · b482b9a5
  Michael Goin authored Aug 02, 2024
  
  b482b9a5
01 Aug, 2024 1 commit
- [Kernel][RFC] Refactor the punica kernel based on Triton (#5036) · 7ecee343
  Jee Jee Li authored Aug 01, 2024
  
  7ecee343
31 Jul, 2024 1 commit
- update benchmarks and examples · 1190e964
  zhuwenwen authored Jul 31, 2024
  
  1190e964
25 Jul, 2024 2 commits
- update attention kernels and version · 0e640807
  zhuwenwen authored Jul 25, 2024
  
  0e640807
- update version · 69341fde
  zhuwenwen authored Jul 25, 2024
  
  69341fde
16 Jul, 2024 1 commit
- fix import error · 6fa22430
  zhuwenwen authored Jul 16, 2024
  
  6fa22430
14 Jul, 2024 2 commits
- [Feature] vLLM CLI (#5090) · dbfe254e
  Ethan Xu authored Jul 14, 2024
```
Co-authored-by: simon-mo <simon.mo@hey.com>
```
  dbfe254e
- [ci][build] fix commit id (#6420) · ccd3c045
  youkaichao authored Jul 14, 2024
```
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  ccd3c045
12 Jul, 2024 1 commit
- [Misc] Add generated git commit hash as `vllm.__commit__` (#6386) · 111fc6e7
  Michael Goin authored Jul 12, 2024
  
  111fc6e7
28 Jun, 2024 1 commit
- [Hardware][Intel] OpenVINO vLLM backend (#5379) · 57f09a41
  Ilya Lavrenov authored Jun 28, 2024
  
  57f09a41
17 Jun, 2024 1 commit

[Hardware][Intel GPU] Add Intel GPU(XPU) inference backend (#3814) · 728c4c8a

Kunshang Ji authored Jun 18, 2024

Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Abhilash Majumder <abhilash.majumder@intel.com>
Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>

728c4c8a

13 Jun, 2024 2 commits
- [Misc] Add vLLM version getter to utils (#5098) · 03dccc88
  Cyrus Leung authored Jun 14, 2024
  
  03dccc88
- [ci] Use sccache to build images (#5419) · 916d219d
  Kevin H. Luu authored Jun 12, 2024
```
Signed-off-by: kevin <kevin@anyscale.com>
```
  916d219d
12 Jun, 2024 1 commit
- [Hardware] Initial TPU integration (#5292) · 1a8bfd92
  Woosuk Kwon authored Jun 12, 2024
  
  1a8bfd92
11 Jun, 2024 1 commit
- [Misc] Remove VLLM_BUILD_WITH_NEURON env variable (#5389) · 8bab4959
  Woosuk Kwon authored Jun 11, 2024
  
  8bab4959
09 Jun, 2024 1 commit
- [Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047) · 5467ac31
  bnellnm authored Jun 09, 2024
  
  5467ac31
03 Jun, 2024 1 commit
- update version · 1dba29d3
  zhuwenwen authored Jun 03, 2024
  
  1dba29d3
02 Jun, 2024 1 commit
- [Kernel][ROCm][AMD] enable fused topk_softmax kernel for moe layer (#4927) · a66cf40b
  Divakar Verma authored Jun 02, 2024
```
This PR enables the fused topk_softmax kernel used in moe layer for HIP
```
  a66cf40b
01 Jun, 2024 1 commit
- [CI/Build] CMakeLists: build all extensions' cmake targets at the same time (#5034) · a360ff80
  Daniele authored Jun 01, 2024
  
  a360ff80
29 May, 2024 1 commit
- [Core][Optimization] remove vllm-nccl (#5091) · 5bd3c650
  youkaichao authored May 28, 2024
  
  5bd3c650
25 May, 2024 1 commit
- update version · 408f0a79
  zhuwenwen authored May 25, 2024
  
  408f0a79
22 May, 2024 2 commits
- fix make error · 09bcf00b
  zhuwenwen authored May 22, 2024
  
  09bcf00b
- skip fp8 · fd6bc480
  zhuwenwen authored May 22, 2024
  
  fd6bc480
13 May, 2024 1 commit
- [Frontend] [Core] perf: Automatically detect vLLM-tensorized model, update... · 8bc68e19
  Sanger Steel authored May 13, 2024
```
[Frontend] [Core] perf: Automatically detect vLLM-tensorized model, update `tensorizer` to version 2.9.0 (#4208)
```
  8bc68e19
12 May, 2024 1 commit
- update cmake args · dbb2e382
  zhuwenwen authored May 12, 2024
  
  dbb2e382
09 May, 2024 1 commit
- [ROCm] Add support for Punica kernels on AMD GPUs (#3140) · ff5abcd7
  kliuae authored May 10, 2024
```
Co-authored-by: miloice <jeffaw99@hotmail.com>
```
  ff5abcd7
08 May, 2024 1 commit
- [Misc] Use vllm-flash-attn instead of flash-attn (#4686) · 89579a20
  Woosuk Kwon authored May 08, 2024
  
  89579a20
03 May, 2024 1 commit
- [Misc] add installation time env vars (#4574) · 344bf7cd
  youkaichao authored May 03, 2024
  
  344bf7cd
02 May, 2024 1 commit
- [Misc] Exclude the `tests` directory from being packaged (#4552) · 5ad60b0c
  Hu Dong authored May 03, 2024
  
  5ad60b0c
01 May, 2024 1 commit
- [CI/Build][Bugfix] VLLM_USE_PRECOMPILED should skip compilation (#4534) · 8b798eec
  Travis Johnson authored May 01, 2024
```
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
```
  8b798eec
30 Apr, 2024 1 commit
- [Frontend] [Core] Tensorizer: support dynamic `num_readers`, update version (#4467) · 715c2d85
  Alpay Ariyak authored Apr 30, 2024
  
  715c2d85
26 Apr, 2024 1 commit
- [CI] Disable non-lazy string operation on logging (#4326) · a88081bf
  SangBin Cho authored Apr 26, 2024
```
Co-authored-by: Danny Guinther <dguinther@neuralmagic.com>
```
  a88081bf