bump llama.cpp to 2293f95ea: prefill attention keeps its rate at long context, +28 % at 24k tokens on Qwen3-4B (fixes #1989) - #2033

bump llama.cpp to 2293f95ea: prefill attention keeps its rate at long context, +28 % at 24k tokens on Qwen3-4B (fixes #1989)#2033

bong-water-water-bong merged 1 commit into

main1bit-MONSTER/engine:mainfrom

1bit/1989-bump-llama-2293f95ea1bit-MONSTER/engine:1bit/1989-bump-llama-2293f95eaCopy head branch name to clipboard