Actions: ggml-org/llama.cpp
Actions
9,176 workflow run results
9,176 workflow run results
reduce_rows_f32 kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n
CI
#25959:
Pull request #15132
synchronize
by
ORippler
ProTip!
You can narrow down the results and go further in time using created:<2025-08-11 or the other filters available.