ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 10:21:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
3afd0600a1cdcd4b53238bc46695e66ec378cdcb
ik_llama.cpp/github-data/pull_requests/108 - Another Bitnet performance improvement on Metal.md
Thomas 0451f10a42 Add GitHub data: filename sanitization (#640)
2025-07-23 13:31:53 +02:00

445 B
Raw Blame History

🔀 #108 - Another Bitnet performance improvement on Metal

Author ikawrakow
State ❌ Closed
Created 2024-10-26
Updated 2024-10-26

Description

This time just the dequantize function.

For Bitnet-1.58b-3B on 30-core M2-Max GPU

  • IQ1_BN goes from 702 t/s to 716 t/s
  • IQ2_BN goes from 714 t/s to 743 t/s
Reference in New Issue View Git Blame Copy Permalink