Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Feature Request] Multi-Head Latent Attention(DeepSeek) support on CPU/NPU #23925

Open
bkaruman opened this issue Mar 6, 2025 · 0 comments
Open

[Feature Request] Multi-Head Latent Attention(DeepSeek) support on CPU/NPU #23925

bkaruman opened this issue Mar 6, 2025 · 0 comments
Labels
feature request request for unsupported feature or enhancement platform:mobile issues related to ONNX Runtime mobile; typically submitted using template

Comments

@bkaruman
Copy link

bkaruman commented Mar 6, 2025

Describe the feature request

DeepSeek's models use Multi-head Latent Attention, the current ONNX model https://huggingface.co/onnxruntime/DeepSeek-R1-Distill-ONNX release leverages GroupQueryAttention.

Is MLA on roadmap for ONNXRT?

Describe scenario use case

Lower KV cache footprint with Multi-Head Latent Attention improving mobile and edge inference
@bkaruman bkaruman added the feature request request for unsupported feature or enhancement label Mar 6, 2025
@github-actions github-actions bot added the platform:mobile issues related to ONNX Runtime mobile; typically submitted using template label Mar 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
feature request request for unsupported feature or enhancement platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@bkaruman