CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda : add f32 to bf16 copy op (#12806)

Browse Source 
This allows BF16 KV-cache on CUDA.
This commit is contained in:
Sigbjørn Skjæret
2025-04-08 23:21:31 +02:00
committed by GitHub
parent b32efad2bc
commit 7538246e7c
2 changed files with 24 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -3079,6 +3079,9 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
if (src0_type == GGML_TYPE_F32 && src1_type == GGML_TYPE_F32) {
return true;
}
if (src0_type == GGML_TYPE_F32 && src1_type == GGML_TYPE_BF16) {
return true;
}
if (src0_type == GGML_TYPE_F32 && src1_type == GGML_TYPE_F16) {
return true;
}