mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-04-16 03:26:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml: disable CUDA graphs for unsupported DUP and CONT node types (#12891)

Browse Source 
Fixes #12798
This commit is contained in:
Alan Gray 2025-04-13 22:12:21 +01:00 committed by GitHub
parent 71e90e8813
commit 307bfa253d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@ -2488,10 +2488,10 @@ static bool check_node_graph_compatibility_and_refresh_copy_ops(ggml_backend_cud
#endif
}
if (node->op == GGML_OP_MUL_MAT_ID) {
if (node->op == GGML_OP_MUL_MAT_ID || node->op == GGML_OP_CONT || node->op == GGML_OP_DUP) {
use_cuda_graph = false; // This node type is not supported by CUDA graph capture
#ifndef NDEBUG
GGML_LOG_DEBUG("%s: disabling CUDA graphs due to mul_mat_id\n", __func__);
GGML_LOG_DEBUG("%s: disabling CUDA graphs due to unsupported node type\n", __func__);
#endif
}