feat: add Kubernetes manifests for AI stack deployment including Qdrant, vLLM, and Triton
This commit is contained in:
@@ -136,7 +136,7 @@ spec:
|
||||
- "--served-model-name"
|
||||
- "Qwen2.5-7B-Instruct"
|
||||
- "--quantization"
|
||||
- "awq_marlin"
|
||||
- "awq"
|
||||
- "--dtype"
|
||||
- "half"
|
||||
- "--max-model-len"
|
||||
|
||||
Reference in New Issue
Block a user