diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-11 11:19:00 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-11 11:19:00 +0100 |
| commit | e0adb8b1227dd4622a91a5b3680b4af2e36d32f4 (patch) | |
| tree | 38a28c4e8b948d32495a82dddad6e63d894568a6 /examples/quantize/quantize.cpp | |
| parent | a63a96b5aea031f9dabf1e7c8d5ee28af170e9e7 (diff) | |
Q3_K_R4 (#134)
* q3_k_r4: Zen4 works, but not as good as it should be
238 t/s, so sloghtly slower than q6_k_r4.
* q3_k_r4: NEON
We get PP-512(LLaMA-3.1-8B) = 106.9 t/s.
This is 1.93X faster than q3_K_S!
---------
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 db0fc0d4..2c8b33c2 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -36,6 +36,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "IQ3_S", LLAMA_FTYPE_MOSTLY_IQ3_S, " 3.44 bpw quantization", }, { "IQ3_M", LLAMA_FTYPE_MOSTLY_IQ3_M, " 3.66 bpw quantization mix", }, { "Q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M, "alias for Q3_K_M" }, + { "Q3_K_R4", LLAMA_FTYPE_MOSTLY_Q3_K_R4, "Q3_K_S repacked" }, { "IQ3_XS", LLAMA_FTYPE_MOSTLY_IQ3_XS, " 3.3 bpw quantization" , }, { "Q3_K_S", LLAMA_FTYPE_MOSTLY_Q3_K_S, " 2.75G, +0.5551 ppl @ LLaMA-v1-7B", }, { "Q3_K_M", LLAMA_FTYPE_MOSTLY_Q3_K_M, " 3.07G, +0.2496 ppl @ LLaMA-v1-7B", }, |