Skip to content

Commit

Permalink
Allow vllm-xft microservice to be accessed externally (#226)
Browse files Browse the repository at this point in the history
* add preload env in run.sh

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

* Allow vllm-xft microservice to be accessed externally

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

---------

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
  • Loading branch information
lvliang-intel authored Jun 21, 2024
1 parent 309c2da commit fe5f394
Show file tree
Hide file tree
Showing 2 changed files with 2 additions and 2 deletions.
2 changes: 1 addition & 1 deletion comps/llms/text-generation/vllm-xft/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ docker build -t opea/llm-vllm-xft:latest --build-arg https_proxy=$https_proxy --
## 2 Run Docker with CLI

```bash
docker run -it -p 9000:9000 -v /home/sdp/Qwen2-7B-Instruct/:/Qwen2-7B-Instruct/ -e vLLM_LLM_ENDPOINT="http://localhost:18688" -e HF_DATASET_DIR="/Qwen2-7B-Instruct/" -e OUTPUT_DIR="./output" -e TOKEN_PATH="/Qwen2-7B-Instruct/" -e https_proxy=$https_proxy -e http_proxy=$http_proxy --ipc=host opea/llm-vllm-xft:latest
docker run -it -p 9000:9000 -v /home/sdp/Qwen2-7B-Instruct/:/Qwen2-7B-Instruct/ -e vLLM_LLM_ENDPOINT="http://localhost:18688" -e HF_DATASET_DIR="/Qwen2-7B-Instruct/" -e OUTPUT_DIR="./output" -e TOKEN_PATH="/Qwen2-7B-Instruct/" -e https_proxy=$https_proxy -e http_proxy=$http_proxy -e no_proxy=$no_proxy --ipc=host opea/llm-vllm-xft:latest
```

# 🚀3. Consume LLM Service
Expand Down
2 changes: 1 addition & 1 deletion comps/llms/text-generation/vllm-xft/run.sh
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ python -m vllm.entrypoints.openai.api_server \
--dtype bf16 \
--kv-cache-dtype fp16 \
--served-model-name xft \
--host localhost \
--host 0.0.0.0 \
--port 18688 \
--trust-remote-code &

Expand Down

0 comments on commit fe5f394

Please sign in to comment.