dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

feat(vllm): expose 'load_format' (#3943)

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-10-23 15:34:57 +02:00 • committed by GitHub
parent c75ecfa009
commit ae1ec4e096
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 4 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
backend/python/vllm/backend.py
View file

@ -95,6 +95,8 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
if request.Quantization != "":
engine_args.quantization = request.Quantization
if request.LoadFormat != "":
engine_args.load_format = request.LoadFormat
if request.GPUMemoryUtilization != 0:
engine_args.gpu_memory_utilization = request.GPUMemoryUtilization
if request.TrustRemoteCode: