Bump vLLM version + more options when loading models in vLLM (#1782)

* Bump vLLM version to 0.3.2

* Add vLLM model loading options

* Remove transformers-exllama

* Fix install exllama
This commit is contained in:
Ludovic Leroux 2024-03-01 16:48:53 -05:00 committed by GitHub
parent 1c312685aa
commit 939411300a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 736 additions and 641 deletions

File diff suppressed because one or more lines are too long

View file

@ -79,7 +79,7 @@ dependencies:
- pypinyin==0.49.0
- python-multipart==0.0.6
- regex==2023.10.3
- safetensors==0.4.0
- safetensors>=0.4.0
- semantic-version==2.10.0
- soundfile==0.12.1
- starlette==0.27.0