Files
llama.cpp/ggml/src
Jeff Bolz a91a41364b vulkan: optimize coopmat2 dequant functions (#10855)
Change the code to do 16b loads when possible and extract the appropriate
component late, so the code is effectively decoding a pair of elements and
then selecting one. This can allow more commoning to happen in the compiler
when neighboring elements are loaded.
2024-12-21 08:04:45 +01:00
..
2024-12-17 19:09:35 +01:00
2024-12-18 19:27:21 +02:00