diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-12 16:04:20 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-12 16:04:20 +0100 |
| commit | 2700d3af36e5ce11f6c2c9644130635f83bae6d5 (patch) | |
| tree | 7e3a65fd9c8318fd654f83f7431b906cc017b34a /examples/quantize/quantize.cpp | |
| parent | aecc95c0cabc6604642e7bc4a8c9e5cb5233ebc4 (diff) | |
IQ4_K_R4 (#138)
* iq4_k_r4: WIP
* iq4_k_r4: Zen4 and hopefully AVX2
On Zen4 we get PP-512(LLaMA-3.1-8B) = 232.6 t/s, up from 182.2 t/s
for iq4_k. Applying the extra shift costs a ~6 performance penalty.
* iq4_k_r4: AVX2
PP-512 = 227.60 t/s. The shifts are really costly.
* iq4_k_r4: NEON
We get PP-512(LLaMA-3.1-8B) = 108 t/s, up from 58.2 t/s for iq4_k.
---------
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 4c650b87..f1e3902c 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -57,6 +57,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "IQ3_K", LLAMA_FTYPE_MOSTLY_IQ3_K, " 3.44 bpw non-linear quantization", }, { "IQ3_KL", LLAMA_FTYPE_MOSTLY_IQ3_KL, " 4 bpw non-linear quantization mix",}, { "IQ4_K", LLAMA_FTYPE_MOSTLY_IQ4_K, " 4.5 bpw non-linear quantization", }, + { "IQ4_K_R4", LLAMA_FTYPE_MOSTLY_IQ4_K_R4, "IQ4_K repacked", }, { "IQ5_K", LLAMA_FTYPE_MOSTLY_IQ5_K, " 5.5 bpw non-linear quantization", }, { "IQ6_K", LLAMA_FTYPE_MOSTLY_IQ6_K, " 6.6 bpw non-linear quantization", }, { "Q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M, "alias for Q4_K_M", }, |