8000 CUDA: faster Deepseek FA, add Turing support by JohannesGaessler · Pull Request #13435 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

CUDA: faster Deepseek FA, add Turing support#13435

Merged
JohannesGaessler merged 1 commit intoggml-org:masterfrom
JohannesGaessler:cuda-fa-opt-2
May 14, 2025

Commits

Commits on May 10, 2025
0