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 /examples/quantize/quantize.cpp | |
| 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 'examples/quantize/quantize.cpp')
| -rw-r--r-- | examples/quantize/quantize.cpp | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 333fae36..9e0dc3cf 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -41,6 +41,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "Q3_K_L", LLAMA_FTYPE_MOSTLY_Q3_K_L, " 3.35G, +0.1764 ppl @ LLaMA-v1-7B", }, { "IQ4_NL", LLAMA_FTYPE_MOSTLY_IQ4_NL, " 4.50 bpw non-linear quantization", }, { "IQ4_NL_X4",LLAMA_FTYPE_MOSTLY_IQ4_NL_X4," 4.50 bpw non-linear quantization", }, + { "Q4_0_R4", LLAMA_FTYPE_MOSTLY_Q4_0_R4, " 4.50 bpw non-linear quantization", }, { "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", }, { "IQ4_KS", LLAMA_FTYPE_MOSTLY_IQ4_KS, " 4.25 bpw non-linear quantization", }, { "IQ4_KSS", LLAMA_FTYPE_MOSTLY_IQ4_KSS, " 4.0 bpw non-linear quantization", }, |