iq1_s_r4: Use Q8_K_128 instead of Q8_1_X4 for gemm (AVX2/Zen4)

This commit is contained in:
Iwan Kawrakow
2025-02-08 18:14:00 +02:00
parent 6d7b58eade
commit 6b4d483dd0
6 changed files with 118 additions and 15 deletions

View File

@@ -415,6 +415,7 @@ extern "C" {
GGML_TYPE_Q8_K16 = 147,
GGML_TYPE_Q8_K32 = 148,
GGML_TYPE_Q8_KR8 = 149,
GGML_TYPE_Q8_K128 = 150,
GGML_TYPE_Q4_0_R8 = 202,
GGML_TYPE_Q5_0_R4 = 206,