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

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

View file

@ -139,6 +139,7 @@ func grpcModelOpts(c config.BackendConfig) *pb.ModelOptions {
DraftModel: c.DraftModel,
AudioPath: c.VallE.AudioPath,
Quantization: c.Quantization,
LoadFormat: c.LoadFormat,
GPUMemoryUtilization: c.GPUMemoryUtilization,
TrustRemoteCode: c.TrustRemoteCode,
EnforceEager: c.EnforceEager,