Skip to content

GitLab

Unverified Commit 230b131b authored by Isotr0py's avatar Isotr0py Committed by GitHub
Browse files

[Bugfix][kernels] Fix half2float conversion in gguf kernels (#15995) 


Signed-off-by: default avatarIsotr0py <2037008807@qq.com>
parent 0812d8dd
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 0 deletions
csrc/quantization/gguf/ggml-common.h
View file @ 230b131b
...@@ -1090,6 +1090,11 @@ __device__ __forceinline__ c10::BFloat16 convert_from_half<c10::BFloat16>(half v ...@@ -1090,6 +1090,11 @@ __device__ __forceinline__ c10::BFloat16 convert_from_half<c10::BFloat16>(half v
#endif // defined(__CUDA_ARCH__) && __CUDA_ARCH__ >= 800 #endif // defined(__CUDA_ARCH__) && __CUDA_ARCH__ >= 800
} }
template<>
__device__ __forceinline__ float convert_from_half<float>(half val) {
return __half2float(val);
}
#if defined(USE_ROCM) #if defined(USE_ROCM)
#ifndef __has_builtin #ifndef __has_builtin
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment