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