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 /include | |
| 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 'include')
| -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 f94dcb1a..fc034b3a 100644 --- a/include/llama.h +++ b/include/llama.h @@ -180,6 +180,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_IQ2_KS = 147, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_KSS = 148, // except 1d tensors // + LLAMA_FTYPE_MOSTLY_Q4_0_R4 = 202, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_NL_X4 = 225, // except 1d tensors LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file |