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

@ -126,6 +126,11 @@ message ModelOptions {
// vllm
string Quantization = 40;
float GPUMemoryUtilization = 50;
bool TrustRemoteCode = 51;
bool EnforceEager = 52;
int32 SwapSpace = 53;
int32 MaxModelLen = 54;
string MMProj = 41;