sirius/gcloud-lab
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request #14 from sirius0xdev/fix/vllm-trust-remote-code-2

Browse source 
fix: adjust memory parameters to stop gibberish output
This commit is contained in:
sirius0xdev 2026-04-18 15:40:22 -04:00 • committed by GitHub
commit bdf2e1d1a4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
apps/base/customer1/openclaw/vllm-gemma.yaml
View file

@ -32,8 +32,10 @@ spec:
- "--dtype" - "--dtype"
- "bfloat16" - "bfloat16"
- "--max-model-len" - "--max-model-len"
- "32768" - "8192"
- "--trust-remote-code" - "--trust-remote-code"
- "--gpu-memory-utilization"
- "0.95"
ports: ports:
- containerPort: 8000 - containerPort: 8000
resources: resources: