]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 1b0b078)
ggml-hip: enable -funsafe-math-optimizations (llama/24668)
authorRapidMark <redacted>
Thu, 9 Jul 2026 08:02:26 +0000 (01:02 -0700)
committerGeorgi Gerganov <redacted>
Fri, 10 Jul 2026 10:06:42 +0000 (13:06 +0300)
commitcc7a521508f6aee3b7987ffd33ec6b5d9c7a06f1
treebe0731125c9e30472bfa10cc7c65b1d15c59e9fatree
parent1b0b078a98fb99978332b337ed1580fc53e0e96fcommit | diff
ggml-hip: enable -funsafe-math-optimizations (llama/24668)

CUDA is compiled with fast math and AMD/HIP is not — this flag lets AMD use fast math too.

We can't use -ffast-math: it implies -ffinite-math-only, which won't compile (ggml uses INFINITY for masking) and produces NaNs. -funsafe-math-optimizations gives the speedup without the NaN problems.

Co-authored-by: Mark Caldwell <redacted>
ggml/src/ggml-hip/CMakeLists.txt diff | blob | history
Packaging of ggerganov/whisper.cpp