tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: backwards pass for misc. ops, add tests (#11257)

Browse Source 
* CUDA: backwards pass for misc. ops, add tests

* remove restrict from pointers
This commit is contained in:
Johannes Gäßler
2025-01-16 16:43:38 +01:00
committed by GitHub
parent 681149ced2
commit 9c8dcefe17
18 changed files with 930 additions and 332 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
ggml/src/ggml-cpu/ggml-cpu.cpp
View File

@ -403,6 +403,16 @@ static bool ggml_backend_cpu_device_supports_op(ggml_backend_dev_t dev, const st
op->type != GGML_TYPE_IQ1_M; // missing type_traits.from_float
case GGML_OP_MUL_MAT:
return src1->type == GGML_TYPE_F32 || src1->type == ggml_get_type_traits_cpu(src0->type)->vec_dot_type;
case GGML_OP_SOFT_MAX_BACK: {
if (op->src[0]->type != GGML_TYPE_F32 || op->src[1]->type != GGML_TYPE_F32) {
return false;
}
float max_bias = 0.0f;
memcpy(&max_bias, (const float *) op->op_params + 1, sizeof(float));
return max_bias == 0.0f;
}
case GGML_OP_IM2COL_BACK:
return src0->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_F32;
case GGML_OP_OUT_PROD: