vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-09 18:44:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

ggml : remove ggml_task_type and GGML_PERF (#8017)

Browse source 
* ggml : remove ggml_task_type and GGML_PERF

* check abort_callback on main thread only

* vulkan : remove usage of ggml_compute_params

* remove LLAMA_PERF
This commit is contained in:
slaren 2024-06-24 03:07:59 +02:00 • committed by GitHub
parent e112b610a1
commit 95f57bb5d5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 402 additions and 1082 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama.cpp
View file

@ -12785,12 +12785,6 @@ static int llama_decode_internal(
}
}
#ifdef GGML_PERF
// print timing information per ggml operation (for debugging purposes)
// requires GGML_PERF to be defined
ggml_graph_print(gf);
#endif
// plot the computation graph in dot format (for debugging purposes)
//if (n_past%100 == 0) {
// ggml_graph_dump_dot(gf, NULL, "llama.dot");