alex.a.alves/voxcpm-vllm-omni
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Melhoria de instruções no arquivo README.md

Browse Source
This commit is contained in:
Alex Alves
2026-09-15 14:34:03 +00:00
parent baf9d0e8b3
commit e1b9df282c
1 changed files with 9 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@@ -32,11 +32,14 @@ Valide o acesso à GPU pelo Podman:
```bash ```bash
podman run --rm \ podman run --rm \
--device nvidia.com/gpu=all \ --device nvidia.com/gpu=all \
--security-opt label=disable \ --security-opt=label=disable \
ubuntu \ nvidia/cuda:12.6.3-base-ubi9 \
nvidia-smi -L nvidia-smi -L
``` ```
selecione a opção:
docker.io/nvidia/cuda:12.6.3-base-ubi9
## Build ## Build
```bash ```bash
@@ -50,6 +53,10 @@ podman build --pull=newer \
-f Containerfile . -f Containerfile .
``` ```
selecione a opção:
docker.io/vllm/vllm-omni:v0.28.0
## Executar o servidor ## Executar o servidor
Para acesso apenas local: Para acesso apenas local: