Devon Rifkin fe5b9bb21b lower default num parallel to 2 ...

this is in part to "pay" for #10452, which doubled the default context length. The combination isn't fully neutral though, because even though the old 4x2k limit and the new 2x4k limit are memory equivalent, the 1x fallback is larger with 4k

2025-04-29 02:04:14 -07:00

29 KiB

Raw Blame History

View Raw