ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 02:41:47 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
770f3585c2a6a1b047689a7635f27140239268bc
ik_llama.cpp/ggml-cuda/common.cuh
Iwan Kawrakow 927e251a12 Bitnet(1.75 bpw): higher precision fp8 scale 
Use 3 bits for the exponent and 5 bits for the mantissa.
This makes PPL to be the same as fp16 (but the previous
version with 4 bits for the exponent and mantissa was
good enough for any practical purposes).
2024-06-22 12:02:52 +03:00

29 KiB
Raw Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink