feat: initial commit with vLLM production stack and benchmark tools
This commit is contained in:
+16
@@ -0,0 +1,16 @@
|
||||
# Model weights cache (multi-GB data)
|
||||
models_cache/
|
||||
*.bin
|
||||
*.safetensors
|
||||
|
||||
# Local environment file
|
||||
.env
|
||||
|
||||
# Docker volumes
|
||||
*-data/
|
||||
|
||||
# Python cache & virtualenv
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
.venv/
|
||||
venv/
|
||||
Reference in New Issue
Block a user