public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-05 14:01:22 +02:00
Code Issues Packages Projects Releases Wiki Activity

CPU/CUDA: fix (GQA) mul mat back, add CUDA support (llama/11380)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-02-03 22:00:57 +02:00
committed by Georgi Gerganov
parent 30767b4c4e
commit c262dc80e2
6 changed files with 59 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/ggml-cpu.cpp
+2 -1
View File
@@ -416,7 +416,8 @@ static bool ggml_backend_cpu_device_supports_op(ggml_backend_dev_t dev, const st
case GGML_OP_IM2COL_BACK:
return src0->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_F32;
case GGML_OP_OUT_PROD:
return (src0->type == GGML_TYPE_F32 || ggml_is_quantized(src0->type)) && src1->type == GGML_TYPE_F32;
return (src0->type == GGML_TYPE_F32 || (ggml_is_quantized(src0->type) && src0->ne[2] == src1->ne[2] && src0->ne[3] == src1->ne[3])) &&
src1->type == GGML_TYPE_F32 && op->type == GGML_TYPE_F32;
default:
return true;
}