ggml-org-llama-cpp-mirror/ggml at f771a191ef5d48363cd578b2c9ec14d95d441da2 - ggml-org-llama-cpp-mirror - Gitea: Git with a cup of tea

mozempk/ggml-org-llama-cpp-mirror

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-11 15:30:39 +02:00

Files

T

History

Oliver Simons f771a191ef Restrict (fused) MMVF to 2*ts alignment, and cublas FP8 fo 16-byte

2026-10-09 21:11:12 +02:00

..

Initial CUDA WIP version

2026-10-09 21:07:43 +02:00

WIP OCP FP8 E4M3 support

2026-10-09 21:00:48 +02:00

Restrict (fused) MMVF to 2*ts alignment, and cublas FP8 fo 16-byte

2026-10-09 21:11:12 +02:00

.gitignore

vulkan : cmake integration (#8119 )

2024-07-13 18:12:39 +02:00

CMakeLists.txt

Initial CUDA WIP version

2026-10-09 21:07:43 +02:00