Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion docs/flagrelease_en/model_list.txt
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,6 @@ FlagRelease/HY-MT2-7B-zhenwu-FlagOS
FlagRelease/Hunyuan-A13B-Instruct-FlagOS
FlagRelease/Kimi-K2-Instruct-FlagOS
FlagRelease/Kimi-K2-Thinking-FlagOS
FlagRelease/Kimi-Linear-48B-A3B-Instruct-nvidia-FlagOS
FlagRelease/MiniCPM-V-4-FlagOS
FlagRelease/MiniCPM-V-4-metax-FlagOS
FlagRelease/MiniCPM-o-4.5-ascend-FlagOS
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -49,26 +49,26 @@ modelscope download --model FlagRelease/Seed-OSS-36B-Instruct --local_dir /data/

### Start the Container
```bash
docker run --name flagos -itd \
docker run --name seed-oss-36b-flagos -itd \
--shm-size="32g" \
-v /usr/src:/usr/src \
-v /xxxxxx/Seed-OSS-36B-Instruct:/data/models/Seed-OSS-36B-Instruct \
-v /data/Seed-OSS-36B-Instruct:/data/Seed-OSS-36B-Instruct \
-v /dev:/dev \
--privileged \
--cap-add=ALL \
--pid=host \
--net=host \
-w /workspace \
harbor.baai.ac.cn/external-cooperation/seed-oss-36b-instruct-iluvatar-tree_0.5.1-gems_0.5.2-vllm_0.13.0-plugin_0.1.1-python_3.12.3-torch_2.7.1-pcp_corex-4.4.0-gpu_biv150-driver_4.4.0:2606231643 sleep infinity
docker exec -it flagos /bin/bash
docker exec -it seed-oss-36b-flagos /bin/bash
```
### Start the Server
```bash
export VLLM_PLUGINS=fl
export TRITON_ALL_BLOCKS_PARALLEL=1
export VLLM_FL_FLAGOS_BLACKLIST="sort,masked_fill_,mm,mul,addmm"
export USE_FLAGGEMS=0
nohup vllm serve --model /mnt/data/vllm-plugin-fl/Seed-OSS-36B-Instruct/ --served-model-name seed-oos --port 80000 --tensor-parallel-size 2 --trust-remote-code --max-
nohup vllm serve --model /data/Seed-OSS-36B-Instruct/ --served-model-name seed-oss-36b-flagos --port 80000 --tensor-parallel-size 2 --trust-remote-code --max-
model-len 30000 >vllm.log 2>&1 &
```

Expand All @@ -78,7 +78,7 @@ model-len 30000 >vllm.log 2>&1 &
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "flagOS",
"model": "seed-oss-36b-flagos",
"messages": [{"role": "user", "content": "你好"}]
}'
```
Expand Down