diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-03 06:15:29 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-03 06:15:29 +0100 |
| commit | ccec00939a30aa7762a232ac4dcadba985ef9ee4 (patch) | |
| tree | b308bd1de2b982c37fc7542374fb77efa2abb726 /ggml/include/ggml.h | |
| parent | 239a344f9935cb614c6208000edb0815214286a1 (diff) | |
Q8_0_R4 (#120)
* Adding q8_0_r4
We get PP-512(LLaMA-3.1-8B) = 268 t/s on a Ryzen-7950X compared
to 175.6 t/s for Q8_0.
* q8_0_r4: NEON
We get PP-512(LLaMA-3.1-8B) = 112.6 t/s on M2-Max.
* q8_0_r4: Zen4 matrix-vector specialization
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/include/ggml.h')
| -rw-r--r-- | ggml/include/ggml.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/ggml/include/ggml.h b/ggml/include/ggml.h index 1a46881a..2358fb76 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -408,6 +408,7 @@ extern "C" { GGML_TYPE_IQ4_KSS = 146, GGML_TYPE_Q4_0_R4 = 202, + GGML_TYPE_Q8_0_R4 = 208, GGML_TYPE_IQ4_NL_X4 = 220, GGML_TYPE_COUNT, }; @@ -469,6 +470,7 @@ extern "C" { GGML_FTYPE_MOSTLY_IQ4_KSS = 139, // except 1d tensors // GGML_FTYPE_MOSTLY_Q4_0_R4 = 202, // except 1d tensors + GGML_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_NL_X4 = 219, // except 1d tensors }; |