root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-13 14:29:52 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

Updated Feature matrix (markdown)

Romain D 2024-03-05 12:48:24 +00:00
parent b1c6785367
commit c0eb5b983a
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Feature-matrix.md

@ -14,4 +14,4 @@
* ²: Only with `-ngl 0`
* ³: Only `-ctk q8_0`, inference is 50% slower
* ⁴: Slower than K-quants of comparable size
* ⁵: Slower than hipBLAS/cuBLAS on similar cards
* ⁵: Slower than cuBLAS/rocBLAS on similar cards