tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-08 01:26:51 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: set_rows + cpy.cu refactor (#14712)

Browse Source
This commit is contained in:
Aman Gupta
2025-07-18 14:54:18 +08:00
committed by GitHub
parent 8f974bc1e9
commit f9a31eea06
4 changed files with 396 additions and 244 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -3226,8 +3226,9 @@ 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 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) &&
return (op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16 || op->type == GGML_TYPE_BF16 ||
op->type == GGML_TYPE_Q4_0 || op->type == GGML_TYPE_Q4_1 || op->type == GGML_TYPE_Q5_0 ||
op->type == GGML_TYPE_Q5_1 || op->type == GGML_TYPE_Q8_0 || op->type == GGML_TYPE_IQ4_NL) &&
op->src[0]->type == GGML_TYPE_F32 &&
op->src[1]->type == GGML_TYPE_I64;
} break;