vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

With mechanism to fall back if graph capture fails

Browse source
This commit is contained in:
Alan Gray 2024-04-30 06:19:51 -07:00
parent d44e0fb22c
commit eb9f15fb6f
2 changed files with 30 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml-cuda/common.cuh
View file

@ -172,7 +172,6 @@
#define GGML_CUDA_MAX_STREAMS 8
[[noreturn]]
void ggml_cuda_error(const char * stmt, const char * func, const char * file, int line, const char * msg);
#define CUDA_CHECK_GEN(err, success, error_fn) \