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

View file

@ -1,7 +1,8 @@
export CONDA_ENV_PATH = "exllama.yml"
.PHONY: exllama
exllama:
$(MAKE) -C ../common-env/transformers
bash install.sh
bash install.sh ${CONDA_ENV_PATH}
.PHONY: run
run: