whisper.cpp/ggml
Justine Tunney 7a96e661e4 ggml : fix overflows in elu function (llama/8866)
It's helpful to use expm1f(x), because expf(x)-1 will result in overflow
for 25% of single-precision floating point numbers.
2024-08-08 22:48:46 +03:00
..
cmake whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
include Fix conversion of unnormalized BF16->BF16 weights (llama/7843) 2024-08-08 22:48:46 +03:00
src ggml : fix overflows in elu function (llama/8866) 2024-08-08 22:48:46 +03:00
.gitignore whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
CMakeLists.txt cann: update cmake (llama/8765) 2024-08-08 22:48:46 +03:00
ggml_vk_generate_shaders.py whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00