bump llama.cpp to a5dc597b8: one-token decode at any head size, and a clang build has its HRX0 again (fixes #1926, #1942) - #1960

bump llama.cpp to a5dc597b8: one-token decode at any head size, and a clang build has its HRX0 again (fixes #1926, #1942)#1960

bong-water-water-bong merged 2 commits into

main1bit-MONSTER/engine:mainfrom

1bit/1926-bump-llama-a5dc597b81bit-MONSTER/engine:1bit/1926-bump-llama-a5dc597b8Copy head branch name to clipboard