Files
ollama-for-amd/llama/patches/0035-vulkan-Fix-crash-when-FP16-mul_mat-accumulation-is-n.patch
Michael Yang 0796d79d19 cuda: skip large batches
cuda panics on batches larger than 1024 so skip those and fallback to
cpu
2025-11-18 16:11:37 -08:00

3.2 KiB