diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-20 12:02:42 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-20 12:02:42 +0100 |
| commit | 4b53bc876eda6d89890711998b3ab5bf033b2199 (patch) | |
| tree | 4624c21b636cb6c5121ae911c154ff8ed5702791 /include/llama.h | |
| parent | 7254f6d34024b708f15d3e6ce6926a808a4d0cc4 (diff) | |
IQ2_XXS_R4 (#154)
* iq2_xxs_r4: Zen4
Disapointing gain: 134.7 t/s -> 151.1 t/s for PP-512
TG-128 is better: 3.45 -> 4.61 t/s @ 1 thread
* Minor
* iq2_xxs_r4: NEON
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'include/llama.h')
| -rw-r--r-- | include/llama.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/include/llama.h b/include/llama.h index e009ed4e..27d10c14 100644 --- a/include/llama.h +++ b/include/llama.h @@ -188,6 +188,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_Q4_K_R4 = 214, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q5_K_R4 = 216, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q6_K_R4 = 218, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ2_XXS_R4 = 219, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ3_XXS_R4 = 223, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_NL_R4 = 225, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_XS_R4 = 230, // except 1d tensors |