gemma.cpp/util
Jan Wassenberg 5e433e774a 1.1x prefill speedup, revamp threading in preparation for hierarchical parallelism.
Limit thread counts to detected. Add max_clusters arg.
Update detection logic to check for smt0 - previously we pinned to some siblings.

PiperOrigin-RevId: 659755311
2024-08-05 18:50:09 -07:00
..
app.h 1.1x prefill speedup, revamp threading in preparation for hierarchical parallelism. 2024-08-05 18:50:09 -07:00
args.h Lint fix - string append, remove stale TODO 2024-07-08 04:11:21 -07:00
threading.h 1.1x prefill speedup, revamp threading in preparation for hierarchical parallelism. 2024-08-05 18:50:09 -07:00