ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 15:44:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

q8_KV_r8 - repacked q8_KV

Browse Source 
On Zen4 it is slower than q8_k_r8 (292 vs 370 t/s)
This makes no sense whatsoever as the q8_KV_r8 GEMM is
basically the q8_k_r8 GEMM with the unnecessary block stuff
removed (so, one would think that it would be faster).
This commit is contained in:
Iwan Kawrakow
2025-02-18 16:25:25 +02:00
parent c82f4194c3
commit 2b9526c8b6
9 changed files with 215 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -207,6 +207,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_IQ4_K_R4 = 340, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ5_K_R4 = 341, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_KS_R4 = 345, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q8_KV_R8 = 398, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q8_K_R8 = 399, // except 1d tensors
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file