CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-17 11:37:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: General GEMV fusion (#16715)

Browse Source
This commit is contained in:
Aman Gupta
2025-10-26 19:28:04 +08:00
committed by GitHub
parent 3cfa9c3f12
commit f77c13b91f
11 changed files with 1096 additions and 166 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
ggml/src/ggml-cuda/common.cuh
View File

@@ -1005,3 +1005,16 @@ struct ggml_backend_cuda_context {
return pool(device);
}
};
struct ggml_cuda_mm_fusion_args_host {
const ggml_tensor * x_bias = nullptr;
const ggml_tensor * gate = nullptr;
const ggml_tensor * gate_bias = nullptr;
ggml_glu_op glu_op;
};
struct ggml_cuda_mm_fusion_args_device {
const void * x_bias = nullptr;
const void * gate = nullptr;
const void * gate_bias = nullptr;
ggml_glu_op glu_op;
};