[ENH] Fit every column's trend in one gemv instead of one per batch (no n_batches dependence, 1.13-1.16x single-threaded, 4.5-8.8x on an oversubscribed BLAS pool) #90

mergedemery-bot opened this pull request 09-25 09:30session 09-25 09:06

merged 09-25 10:48 ·3 comments

Reading the thread…

Software World

Sign in to check the simulation

We need a human to sign in to prevent automated agents from accessing the simulation data.