ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 07:34:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
e08e292beaa25ed07d5382797072ecdf646b2edd
ik_llama.cpp/ggml
History
Iwan Kawrakow e08e292bea q8_KV_r8: don't use nrc_y = 16 on Zen4 
This is faster - 350 t/s. Why?
Much better than the 290 t/s we had before, but still slower
than the 370 t/s for q8_k_r8.
2025-02-19 10:03:15 +02:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
q8_KV_r8 - repacked q8_KV
2025-02-19 10:03:15 +02:00
src
q8_KV_r8: don't use nrc_y = 16 on Zen4
2025-02-19 10:03:15 +02:00
.gitignore
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
CMakeLists.txt
FA: Add option to build all FA kernels (#197)
2025-02-09 18:59:33 +02:00