Jesse Gross 22d6c817f8 mlxrunner: fuse top-P and top-K into a single sort pass ...

When both filters are active, avoid paying for a full sort in top-P
and a partial sort in top-K. Single-filter paths are unchanged.
Improves generation throughput on gemma4:e4b by 1.5%.

2026-04-20 17:43:00 -07:00

..

logprob_test.go

mlxrunner: add logprobs support

2026-04-20 17:43:00 -07:00

sample_test.go

mlxrunner: add logprobs support

2026-04-20 17:43:00 -07:00

sample.go

mlxrunner: fuse top-P and top-K into a single sort pass

2026-04-20 17:43:00 -07:00