diff options
author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-02 17:01:48 +0100 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-12-02 17:01:48 +0100 |
commit | 239a344f9935cb614c6208000edb0815214286a1 (patch) | |
tree | aaa1933857cd9575fecfec14515e43e24305ce1f /ggml/include/ggml.h | |
parent | 6d0462d4a39085a9f9da04e0a5fc7cc9d4578818 (diff) |
Q4_0_R4 (#119)
* Adding iq4_0_r4 - q4_0 repacked
We get PP-512(LLaMA-3.1-8B) = 278 t/s on a Ryzen-7950X CPU,
so ~5-6% faster than iq4_nl_x4.
* q4_0_r4: NEON
Here we get 115.8 t/s, so also ~5% better than iq4_nl_x4.
---------
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 dabb2264..1a46881a 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -407,6 +407,7 @@ extern "C" { GGML_TYPE_IQ2_KS = 145, GGML_TYPE_IQ4_KSS = 146, + GGML_TYPE_Q4_0_R4 = 202, GGML_TYPE_IQ4_NL_X4 = 220, GGML_TYPE_COUNT, }; @@ -467,6 +468,7 @@ extern "C" { GGML_FTYPE_MOSTLY_IQ2_KS = 138, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_KSS = 139, // except 1d tensors // + GGML_FTYPE_MOSTLY_Q4_0_R4 = 202, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_NL_X4 = 219, // except 1d tensors }; |