CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix n_threads_cur initialization with one thread (#9538)

Browse Source 
* ggml : fix n_threads_cur initialization with one thread

* Update ggml/src/ggml.c

---------

Co-authored-by: Max Krasnyansky <quic_maxk@quicinc.com>
This commit is contained in:
slaren
2024-09-18 19:13:08 +02:00
committed by GitHub
parent 0d2f22e45c
commit 64c6af3195
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/src/ggml.c
View File

@@ -20239,6 +20239,7 @@ enum ggml_status ggml_graph_compute(struct ggml_cgraph * cgraph, struct ggml_cpl
ggml_graph_compute_thread(&threadpool->workers[omp_get_thread_num()]);
}
} else {
atomic_store_explicit(&threadpool->n_threads_cur, 1, memory_order_relaxed);
ggml_graph_compute_thread(&threadpool->workers[0]);
}
#else