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

examples: change GPT-2 KV cache to fp16 to take advantage of tensor cores #1142

Open

bssrdf wants to merge 1 commit into ggml-org:master from bssrdf:make-gpt-2-peform-like-llama-cpp

+2 −2

Contributor

bssrdf commented Mar 12, 2025

This PR changed default KV cache type to FP16 to use tensor cores if available. This brings the inference performance much closer to llama.cpp.


          change KV cache to fp16 to take advantage of tensor cores

1d0184f

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet