-
-
Notifications
You must be signed in to change notification settings - Fork 5
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Steps to use with vllm and triton server
- Loading branch information
1 parent
46f808f
commit a6bc12e
Showing
2 changed files
with
56 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,37 @@ | ||
Triton Server Setup | ||
|
||
Build Triton | ||
- git clone https://github.com/triton-inference-server/server | ||
- cd server | ||
- python build.py | ||
|
||
Build Mixtral with Tensor RT-LLM | ||
|
||
- git clone https://github.com/NVIDIA/TensorRT-LLM/ | ||
- cd TensorRT-LLM | ||
- cd examples/mixtral | ||
- pip install -r requirements | ||
- git lfs install | ||
- git clone https://huggingface.co/mistralai/Mixtral-8x7B-v0.1 | ||
|
||
|
||
- Build Triton | ||
- https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/customization_guide/build.html | ||
- Security | ||
- https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/customization_guide/deploy.html | ||
- https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/customization_guide/build.html#building-with-docker | ||
|
||
- build mixtral | ||
- https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/mixtral/README.md | ||
- https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/getting_started/quickstart.html | ||
- Build mistral - https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llama#mistral-v01 | ||
|
||
|
||
Extra | ||
- sudo useradd -m llm | ||
- sudo passwd llm | ||
- sudo usermod -aG sudo llm | ||
- apt install python3.10-venv | ||
- apt install python3-pip | ||
- sudo apt-get install build-essential linux-generic libmpich-dev libopenmpi-dev | ||
- sudo apt install openmpi-devel |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,19 @@ | ||
Setup with Vllm | ||
|
||
- Creat account in huggingface > Profile > AccessToken > create new user Access token | ||
|
||
|
||
docker run --gpus all \ | ||
-e HF_TOKEN=$HF_TOKEN -p 8000:8000 \ | ||
ghcr.io/mistralai/mistral-src/vllm:latest \ | ||
--host 0.0.0.0 \ | ||
--model mistralai/Mistral-7B-Instruct-v0.2 | ||
|
||
curl --location 'http://IP:Port/v1/chat/completions' \ | ||
--header 'Content-Type: application/json' \ | ||
--data '{ | ||
"model": "mistralai/Mistral-7B-Instruct-v0.2", | ||
"messages": [ | ||
{"role": "user", "content": "what minimun materials are necessary to build a Seed harvesting robot, show me how to arrange the parts"} | ||
] | ||
}' |