mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-29 04:44:34 +00:00
18429220bd
* use 128 bit loads (i've tried 256->128 to death and its slower) * double accumulator * avx bf16 vec dot * +3% q4_0 inference * +7% tg +5% pp compared to master * slower f16c version, kep for reference * 256b version, also slow. i tried :) * revert f16 * faster with madd * split to functions * Q8_0 and IQ4_NL, 5-7% faster * fix potential overflow (performance reduced) * 16 bit add for q4_0 only * merge |
||
|---|---|---|
| .. | ||
| include | ||
| src | ||
| .gitignore | ||
| CMakeLists.txt | ||