Update README.md
Browse files
README.md
CHANGED
|
@@ -74,19 +74,20 @@ modelscope download --model LLM-Research/phi-4 --local_dir /share/models/phi-4
|
|
| 74 |
### Download FlagOS Image
|
| 75 |
|
| 76 |
```bash
|
| 77 |
-
docker pull harbor.baai.ac.cn/flagrelease-public/
|
| 78 |
```
|
| 79 |
|
| 80 |
### Start the inference service
|
| 81 |
|
| 82 |
```bash
|
| 83 |
#Container Startup
|
| 84 |
-
docker run --rm --init --detach --net=host --uts=host --ipc=host --security-opt=seccomp=unconfined --privileged=true --ulimit stack=67108864 --ulimit memlock=-1 --ulimit nofile=1048576:1048576 --shm-size=32G -v /share:/share --gpus all --name flagos
|
| 85 |
```
|
| 86 |
|
| 87 |
### Serve
|
| 88 |
|
| 89 |
```bash
|
|
|
|
| 90 |
flagscale serve phi_4
|
| 91 |
|
| 92 |
```
|
|
|
|
| 74 |
### Download FlagOS Image
|
| 75 |
|
| 76 |
```bash
|
| 77 |
+
docker pull harbor.baai.ac.cn/flagrelease-public/flagrelease-nvidia-release-model_phi-4-tree_none-gems_3.0-scale_0.8.0-cx_none-python_3.12.3-torch_2.7.1-pcp_cuda12.9-gpu_nvidia005-arc_amd64-driver_570.124.06:2508271640
|
| 78 |
```
|
| 79 |
|
| 80 |
### Start the inference service
|
| 81 |
|
| 82 |
```bash
|
| 83 |
#Container Startup
|
| 84 |
+
docker run --rm --init --detach --net=host --uts=host --ipc=host --security-opt=seccomp=unconfined --privileged=true --ulimit stack=67108864 --ulimit memlock=-1 --ulimit nofile=1048576:1048576 --shm-size=32G -v /share:/share --gpus all --name flagos harbor.baai.ac.cn/flagrelease-public/flagrelease-nvidia-release-model_phi-4-tree_none-gems_3.0-scale_0.8.0-cx_none-python_3.12.3-torch_2.7.1-pcp_cuda12.9-gpu_nvidia005-arc_amd64-driver_570.124.06:2508271640 sleep infinity
|
| 85 |
```
|
| 86 |
|
| 87 |
### Serve
|
| 88 |
|
| 89 |
```bash
|
| 90 |
+
docker exec -it flagos bash
|
| 91 |
flagscale serve phi_4
|
| 92 |
|
| 93 |
```
|