Skip to content

CUDA/HIP: refractor mmqv to unify the calculation of nwarps and rows per block between host and device code.#12177

Merged
IMbackK merged 5 commits intoggml-org:masterfrom IMbackK:refactor_mmqvMar 11, 2025

Commits

Commits on Mar 6, 2025

Commits on Mar 7, 2025