update
This commit is contained in:
+2
-2
@@ -8,7 +8,7 @@ services:
|
||||
env_file:
|
||||
- .env
|
||||
volumes:
|
||||
- models:/models:ro
|
||||
- /var/models:/models:ro
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
@@ -22,7 +22,7 @@ services:
|
||||
exec python3 -m vllm.entrypoints.openai.api_server
|
||||
--model "$$MODEL_PATH"
|
||||
--served-model-name "$$SERVED_NAME"
|
||||
--host 0.0.0.0 --port 8000
|
||||
--host 0.0.0.0 --port "$LISTEN_PORT"
|
||||
--tensor-parallel-size "$$TP_SIZE"
|
||||
--dtype "$$DTYPE"
|
||||
--max-model-len "$$MAX_MODEL_LEN"
|
||||
|
||||
Reference in New Issue
Block a user