Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-03 17:51:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

Remove call to ggml_cuda_mul_mat_get_wsize

Browse Source
This commit is contained in:
Stephan Walter 2023-07-04 19:15:57 +02:00
parent f9c585f008
commit 81f28f2539
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ggml.c
View File

@ -16590,7 +16590,6 @@ void ggml_graph_compute(struct ggml_context * ctx, struct ggml_cgraph * cgraph)
if (ggml_cuda_can_mul_mat(node->src0, node->src1, node)) {
node->n_tasks = 1; // TODO: this actually is doing nothing
// the threads are still spinning
cur = ggml_cuda_mul_mat_get_wsize(node->src0, node->src1, node);
}
else
#elif defined(GGML_USE_CLBLAST)