]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid...
authorMax Krasnyansky <redacted>
Sat, 31 May 2025 22:39:19 +0000 (15:39 -0700)
committerGeorgi Gerganov <redacted>
Sun, 1 Jun 2025 12:14:44 +0000 (15:14 +0300)
commit1e16340f4b9fb32e6b2ee15c8568598eb11dd0ee
tree55c4adfcb05b517948ef78860e9d34f0bfcb5e1a
parent4a502549981e7545e8f5e673625441665a817d25
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (llama/12995)

* threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling

We talked about adding LOW priority for GGML threads in the original threadpool PR.
It might be useful for some cases to avoid contention.

Latest Windows ARM64 releases started parking (offlining) the CPU cores
more aggresively which results in suboptimal performance with n_threads > 4.
To deal with that we now disable Power Throttling for our threads for the NORMAL
and higher priorities.

Co-authored-by: Diego Devesa <redacted>
* threading: disable SetThreadInfo() calls for older Windows versions

* Update tools/llama-bench/llama-bench.cpp

Co-authored-by: Diego Devesa <redacted>
---------

Co-authored-by: Diego Devesa <redacted>
ggml/include/ggml.h
ggml/src/ggml-cpu/ggml-cpu.c