Repository navigation
npu: a launch's result is dequantised with one multiply per element, not one ldexp(): prefill 24.4-25.1 -> 29.8-30.6 tok/s on the served 27B pack (Refs #1990) - #2008
Merged
Annotations
1 notice
|
"The ubuntu-latest label will migrate to Ubuntu 26 beginning October 19, 2026. For more information, see https://github.com/actions/runner-images/issues/14748"
|
background
wait
wait-all
cancel
parallel
Loading