q6_k_r4: 1st functional AVX2 version

This commit is contained in:
Iwan Kawrakow
2024-12-09 20:02:57 +02:00
parent 2dce0267c9
commit 2bd2d0176a
4 changed files with 92 additions and 2 deletions

View File

@@ -184,6 +184,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q5_0_R4 = 208, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_K_R4 = 214, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q6_K_R4 = 218, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_NL_R4 = 225, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_XS_R4 = 230, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q6_0_R4 = 235, // except 1d tensors