bitter-ability-32190
08/09/2022, 2:54 PMhappy-kitchen-89482
08/09/2022, 3:23 PMbitter-ability-32190
08/09/2022, 3:27 PMit should be easy to split that output up and cache individually per-file.There's two halves to inference single v batch: • Rule memoization: If we batch it, it'll invalidate the memoization. No easy way around that, but likely very fast (TM) • Process caching: That's where my other PR of splitting a coalesced process would help this So, even with the coalesced batching, memoization would still be affected
that inference is so cheap that almost the entire time per file is process overhead, then over-invalidating may not matterThat's precisely my hypothesis, which I'm hungry to test in a real-world scenario so that I can push the PR forward with good findings
witty-crayon-22786
08/16/2022, 8:07 PM