mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 22:08:46 +01:00
6d1616944d
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 |
||
|---|---|---|
| .. | ||
| arm64-windows-llvm.cmake | ||
| arm64-windows-msvc.cmake | ||
| FindSIMD.cmake | ||
| llama.pc.in | ||