Georgi Gerganov 6d1616944d ggml : prevent builds with -ffinite-math-only (#7726) ... This enforces a check that -fno-finite-math-only was set and that the operating compiling mode is not in finite maths mode. This is because during rewriting of silu and softmax for cpu #7154 there emerged an issue where the result that was observed when >1 slot was nondeterministic as found by @JohannesGaessler. @LostRuins narrowed the problem down to -ffinite-math-only which was theorised to be due to SiLU, instead of flushing small values to 0, returns NaN or some other garbage. @jart proposed a fix that @ggerganov then implemented in this fix ref https://github.com/ggerganov/llama.cpp/pull/7154#issuecomment-2145661825		2024-06-04 17:01:09 +10:00
..
arm64-windows-llvm.cmake	ggml : prevent builds with -ffinite-math-only (#7726)	2024-06-04 17:01:09 +10:00
arm64-windows-msvc.cmake	Add support for properly optimized Windows ARM64 builds with LLVM and MSVC (#7191)	2024-05-16 12:47:36 +10:00
FindSIMD.cmake	cmake : MSVC instruction detection (fixed up #809) (#3923)	2023-11-05 10:03:09 +02:00
llama.pc.in	cmake : add pkg-config spec file for llama.cpp (#7702)	2024-06-03 11:06:24 +03:00