software-engineering/edge-gitops
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

use vlmm openai

Browse Source
This commit is contained in:
HaimKortovich
2026-05-07 14:59:55 -05:00
parent 2229daa1a3
commit 1a4e73b755
1 changed files with 2 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
clusters/k3s-dgx/nim-service/qwen.yaml
View File

@@ -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: