root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-13 20:14:29 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

cuda : add TODO for calling cublas from kernel + using mem pool

Browse Source
This commit is contained in:
Georgi Gerganov 2023-10-24 16:33:24 +03:00
parent 27c34c0112
commit d798a17c34
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ggml-cuda.cu
View File

@ -7149,6 +7149,7 @@ static void ggml_cuda_mul_mat_mat_batched_cublas(const ggml_tensor * src0, const
CUBLAS_GEMM_DEFAULT_TENSOR_OP)); CUBLAS_GEMM_DEFAULT_TENSOR_OP));
} else { } else {
// use cublasGemmBatchedEx // use cublasGemmBatchedEx
// TODO: https://github.com/ggerganov/llama.cpp/pull/3749#discussion_r1369997000
const int ne23 = ne12*ne13; const int ne23 = ne12*ne13;
// TODO: avoid this alloc // TODO: avoid this alloc