diff options
author | Kawrakow <iwankawrakow@gmail.com> | 2025-05-24 11:48:52 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2025-05-24 11:48:52 +0300 |
commit | a2c42f9985a96abc8b1b4104b0524ea4b2da9363 (patch) | |
tree | b5230cbd3f3aa77013c5abc06ad08c454aa19a55 /convert_hf_to_gguf.py | |
parent | 9fb82af3a80f8b1774afd198e981460dc23b41dc (diff) |
Faster IQ3_KT and IQ4_KT (#453)
* Somewhat faster iq3_kt (AVX2)
* Cleanup
* Slightly faster iq4_kt
* Slightly faster iq4_kt
PP is now almost 50% better than original, TG is ~20% better
* Cleanup
* Very slightly faster iq4_kt TG
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'convert_hf_to_gguf.py')
0 files changed, 0 insertions, 0 deletions