q2_k_r4: Zen4

PP-512(LLaMA-3.1-8B) = 256 t/s
This commit is contained in:
Iwan Kawrakow
2024-12-11 16:28:56 +02:00
parent 9469af87f7
commit 93c6e295ee
10 changed files with 263 additions and 3 deletions

View File

@@ -183,6 +183,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_Q4_0_R4 = 202, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q5_0_R4 = 208, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q2_K_R4 = 210, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q3_K_R4 = 211, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_K_R4 = 214, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q5_K_R4 = 216, // except 1d tensors