frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Isotr0py
2025-04-05 00:38:58 +08:00
committed by GitHub
parent 0812d8dd41
commit 230b131b54
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
csrc/quantization/gguf/ggml-common.h
View File

@ -1090,6 +1090,11 @@ __device__ __forceinline__ c10::BFloat16 convert_from_half<c10::BFloat16>(half v
#endif // defined(__CUDA_ARCH__) && __CUDA_ARCH__ >= 800
}
template<>
__device__ __forceinline__ float convert_from_half<float>(half val) {
return __half2float(val);
}
#if defined(USE_ROCM)
#ifndef __has_builtin