mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-01-26 17:20:01 +00:00
IQ5_KS_R4: row-interleaved IQ5_KS (#426)
* iq5_ks_r4: basics * iq5_ks_r4: Zen4 works * iq5_ks_r4: AVX2 works * iq5_ks_r4: NEON * Fix iq5_ks on NEON --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
@@ -220,6 +220,7 @@ 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_IQ5_KS_R4 = 350, // except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q8_KV_R8 = 398, // except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q8_K_R8 = 399, // except 1d tensors
|
||||
|
||||
|
||||
Reference in New Issue
Block a user