tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : reduce command encoding overhead (#9698)

Browse Source 
* metal : reduce command encoding overhead

ggml-ci

* metal : add comments
This commit is contained in:
Georgi Gerganov
2024-10-01 16:00:25 +03:00
committed by GitHub
parent a90484c6d9
commit cad341d889
5 changed files with 2000 additions and 1912 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/llava/clip.cpp
View File

@ -2444,12 +2444,6 @@ bool clip_image_batch_encode(clip_ctx * ctx, const int n_threads, const clip_ima
ggml_backend_cpu_set_n_threads(ctx->backend, n_threads);
}
#ifdef GGML_USE_METAL
if (ggml_backend_is_metal(ctx->backend)) {
ggml_backend_metal_set_n_cb(ctx->backend, n_threads);
}
#endif
ggml_backend_graph_compute(ctx->backend, gf);
// the last node is the embedding tensor