whisper.cpp/ggml
Johannes Gäßler 60d178cee9 CUDA: only allocate FA tmp buffer if needed (llama/18564) 2026-01-14 09:11:59 +02:00
..
cmake
include vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron (llama/18295) 2026-01-14 09:11:59 +02:00
src CUDA: only allocate FA tmp buffer if needed (llama/18564) 2026-01-14 09:11:59 +02:00
.gitignore
CMakeLists.txt ggml : bump version to 0.9.5 (ggml/1410) 2025-12-31 18:27:20 +02:00