Great work
Thank you very much for your contributions. I’m reaching out to kindly ask if you could share the details of your inference environment.
I’m currently stuck on Sparse MLA / DSA compatibility issue when trying to run the model with vLLM, which is blocking my usage.
testing env:
System: Ubuntu24LTS
Driver: 580.82.07
Graphics Card: 8xH200
Docker Image: Ubuntu22LTS Python3.12 Cuda12.8
install & run
python3.12 -m venv venv
source venv/bin/activate
pip install -U vllm --pre --index-url https://pypi.org/simple --extra-index-url https://wheels.vllm.ai/nightly --force-reinstall
pip install git+https://github.com/huggingface/transformers.git
pip install git+https://github.com/deepseek-ai/DeepGEMM.git@v2.1.1.post3 --no-build-isolation
vllm serve ...
Thank you for your work! I'd like to point out that not all files have been uploaded to the repository yet, almost a third of the volume is missing. I'd like to ask you to check and upload the missing files.
@R-omk
Due to an unknown issue, the upload process showed as completed but resulted in missing weights. I have re-uploaded the files and manually verified their integrity. Please download the latest weights. If there are any further issues, please continue reporting them to our team.