We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 3e9b70a commit 97b391dCopy full SHA for 97b391d
docs/tutorials/deploy-with-gpu.mdx
@@ -69,7 +69,7 @@ services:
69
image: ghcr.io/mistralai/mistral-src/vllm:latest
70
ports:
71
- mode: host
72
- - target: 8000
+ target: 8000
73
// highlight-next-line
74
command: ["--host","0.0.0.0","--model","TheBloke/Mistral-7B-Instruct-v0.2-AWQ","--quantization","awq","--dtype","auto","--tensor-parallel-size","1","--gpu-memory-utilization",".95","--max-model-len","8000"]
75
deploy:
0 commit comments