CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda : add set rows for bf16 (#14664)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-07-13 15:01:24 +02:00
committed by GitHub
parent e743cddb60
commit 923e3ea2e3
2 changed files with 17 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -3226,8 +3226,8 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
} break;
case GGML_OP_SET_ROWS:
{
#pragma message("TODO: implement BF16, Q4_0, Q4_1, Q5_0, Q5_1, Q8_0, IQ4_NL support (https://github.com/ggml-org/llama.cpp/pull/14661)")
return (op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16) &&
#pragma message("TODO: implement Q4_0, Q4_1, Q5_0, Q5_1, Q8_0, IQ4_NL support (https://github.com/ggml-org/llama.cpp/pull/14661)")
return (op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16 || op->type == GGML_TYPE_BF16) &&
op->src[0]->type == GGML_TYPE_F32 &&
op->src[1]->type == GGML_TYPE_I64;
} break;