public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

CUDA: only support F32/F16 for GGML_OP_REPEAT (llama/24533)

This commit is contained in:
leonardHONG 2026-06-15 14:11:00 +08:00 committed by Georgi Gerganov
parent 3e0b917514
commit 7349e5ae11
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -5337,8 +5337,9 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
} break;
case GGML_OP_REPEAT:
{
// the CUDA REPEAT path only implements F32/F16; other types assert at runtime
ggml_type src0_type = op->src[0]->type;
return src0_type != GGML_TYPE_I32 && src0_type != GGML_TYPE_I16;
return src0_type == GGML_TYPE_F32 || src0_type == GGML_TYPE_F16;
} break;
case GGML_OP_REPEAT_BACK:
return op->type == GGML_TYPE_F32 && (op->src[0]->ne[2]*op->src[0]->ne[3]) <= (1 << 15);