use vlmm openai
This commit is contained in:
@@ -60,11 +60,9 @@ spec:
|
||||
- "--enable-prefix-caching"
|
||||
- '--speculative-config={"method":"mtp","num_speculative_tokens":2}'
|
||||
image:
|
||||
repository: nvcr.io/nim/nvidia/llm-nim
|
||||
tag: "1.12"
|
||||
repository: vllm/vllm-openai
|
||||
tag: "v0.19.1-cu130"
|
||||
pullPolicy: IfNotPresent
|
||||
pullSecrets:
|
||||
- ngc-secret
|
||||
authSecret: hf-api-secret
|
||||
storage:
|
||||
nimCache:
|
||||
|
||||
Reference in New Issue
Block a user