Instructions to use deepseek-ai/deepseek-vl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepseek-ai/deepseek-vl2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="deepseek-ai/deepseek-vl2")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("deepseek-ai/deepseek-vl2", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use deepseek-ai/deepseek-vl2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "deepseek-ai/deepseek-vl2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/deepseek-vl2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/deepseek-ai/deepseek-vl2
- SGLang
How to use deepseek-ai/deepseek-vl2 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "deepseek-ai/deepseek-vl2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/deepseek-vl2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "deepseek-ai/deepseek-vl2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/deepseek-vl2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use deepseek-ai/deepseek-vl2 with Docker Model Runner:
docker model run hf.co/deepseek-ai/deepseek-vl2
deepseek_vl2 error
i installed deepseek_vlhttps://github.com/deepseek-ai/DeepSeek-VL2/tree/main from github
but this code does not work:
from deepseek_vl.models import DeepseekVLV2Processor
from deepseek_vl.utils.io import load_pil_images
yet, it should be:
from deepseek_vl2.models import DeepseekVLV2Processor
from deepseek_vl2.utils.io import load_pil_images
then it started to find appropriate modules. Please update your code.
Hi @bako96 ,
I have already changed the above lines but I am getting many errors while I'm trying to get it to run. Were you able to run everything seamlessly?
Hi @bako96 ,
I have already changed the above lines but I am getting many errors while I'm trying to get it to run. Were you able to run everything seamlessly?
Unfortunately no, it needs to be "xformers" installed. You should include this in your image which i did not. Or you can use flash attention too if possible.
I am facing the same issue. Were you guys able to resolve the issue?