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 /ggml/include/ggml.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 'ggml/include/ggml.h')
| -rw-r--r-- | ggml/include/ggml.h | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/ggml/include/ggml.h b/ggml/include/ggml.h index 90d34b40..42fbcea2 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -418,6 +418,7 @@ extern "C" { GGML_TYPE_Q4_K_R4 = 212, GGML_TYPE_Q5_K_R4 = 213, GGML_TYPE_Q6_K_R4 = 214, + GGML_TYPE_IQ2_XXS_R4= 216, GGML_TYPE_IQ3_XXS_R4= 218, GGML_TYPE_IQ4_NL_R4 = 220, GGML_TYPE_IQ4_XS_R4 = 223, @@ -495,8 +496,9 @@ extern "C" { GGML_FTYPE_MOSTLY_Q2_K_R4 = 210, // except 1d tensors GGML_FTYPE_MOSTLY_Q3_K_R4 = 211, // except 1d tensors GGML_FTYPE_MOSTLY_Q4_K_R4 = 212, // except 1d tensors - GGML_FTYPE_MOSTLY_Q5_K_R4 = 215, // except 1d tensors + GGML_FTYPE_MOSTLY_Q5_K_R4 = 213, // except 1d tensors GGML_FTYPE_MOSTLY_Q6_K_R4 = 214, // except 1d tensors + GGML_FTYPE_MOSTLY_IQ2_XXS_R4= 215, // except 1d tensors GGML_FTYPE_MOSTLY_IQ3_XXS_R4= 217, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_NL_R4 = 219, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_XS_R4 = 222, // except 1d tensors |