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

force backend

Browse Source
This commit is contained in:
HaimKortovich
2026-05-07 15:29:45 -05:00
parent 6491c6cebe
commit 4dc4fc5fdf
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
clusters/k3s-dgx/nim-service/qwen.yaml
View File

@@ -47,6 +47,8 @@ metadata:
namespace: nim-service namespace: nim-service
spec: spec:
env: env:
- name: NIM_BACKEND
value: vllm
- name: NIM_PASSTHROUGH_ARGS - name: NIM_PASSTHROUGH_ARGS
value: "--gpu-memory-utilization 0.85 --served-model-name qwen36 --max-model-len 256K --language-model-only --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --enable-chunked-prefill --max-num-batched-tokens 32768 --max-num-seqs 10 --enable-prefix-caching --speculative-config '{\"method\":\"mtp\",\"num_speculative_tokens\":2}'" value: "--gpu-memory-utilization 0.85 --served-model-name qwen36 --max-model-len 256K --language-model-only --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --enable-chunked-prefill --max-num-batched-tokens 32768 --max-num-seqs 10 --enable-prefix-caching --speculative-config '{\"method\":\"mtp\",\"num_speculative_tokens\":2}'"
image: image:
@@ -59,7 +61,6 @@ spec:
storage: storage:
nimCache: nimCache:
name: qwen36-27b-fp8 name: qwen36-27b-fp8
profile: vllm
replicas: 1 replicas: 1
resources: resources:
limits: limits: