diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-02 07:25:39 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-02 07:25:39 +0100 |
| commit | 6d0462d4a39085a9f9da04e0a5fc7cc9d4578818 (patch) | |
| tree | b7fd71bda09bb8e2315feff8b6128ad0b7cbefc7 /include/llama.h | |
| parent | 8ad84b9fab9570c36220cb791f9a67a4d2c7fd2f (diff) | |
IQ4_NL_X4 (#118)
* Adding iq4_nl_x4
Looks very promising - I get PP-512(LLaMA-3.1-8B) = 230 t/s
on the Ryzen-7950X! This is faster than any other quant and
~40% faster than iq4_nl.
* iq4_nl_x4: getting amazing
This Zen4 variant gets us to PP-512(LLaMA-3.1-8B) = 263 t/s!
* iq4_nl_x4: AVX2
Here we gain only 25% compared to iq4_nl
* iq4_nl_x4: NEON
On M2-Max we get PP-512(LLaMA-3.1-8B) = 109.7 t/s, up from
82.4 t/s for iq4_nl.
* iq4_nl_x4: minor NEON improvement and cleanup
This gets us to 110.3 t/s. In comparison,
IQ4_NL_4_4 in mainline llama.cpp achieves 92.3 t/s.
* iq4_nl_x4: NEON specialization for matrix x vector
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'include/llama.h')
| -rw-r--r-- | include/llama.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/include/llama.h b/include/llama.h index 965e5f50..f94dcb1a 100644 --- a/include/llama.h +++ b/include/llama.h @@ -179,6 +179,8 @@ extern "C" { LLAMA_FTYPE_MOSTLY_IQ3_KL = 146, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ2_KS = 147, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_KSS = 148, // except 1d tensors + // + LLAMA_FTYPE_MOSTLY_IQ4_NL_X4 = 225, // except 1d tensors LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file }; |