Jeff Bolz 8539d72ffa vulkan: FA MMQ should use fp32 for Q quantization calculations (llama/27413) ... Codex found that qd could be a denorm and 1/qd would overflow.		2026-08-21 19:23:26 +03:00
..
cmake	cmake : add config version support (ggml/1582)	2026-08-14 22:16:06 +03:00
include	ggml: add ggml_rope_set_offset (+ metal support) (llama/27120)	2026-08-21 19:23:26 +03:00
src	vulkan: FA MMQ should use fp32 for Q quantization calculations (llama/27413)	2026-08-21 19:23:26 +03:00
.gitignore	…
CMakeLists.txt	CI: Use LLVM's OpenMP over MSVC_DEBUG_non_redist on Windows (llama/26678)	2026-08-21 19:23:26 +03:00