diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-02-05 13:49:39 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-02-05 13:49:39 +0200 |
| commit | 8b7536bda8b65107794c4df710f14ddfde430160 (patch) | |
| tree | 97a9dea70458bddcef51c734e22026ac51b51ed7 /examples | |
| parent | ecf111a11ca56ff0731308f94bd6c5e96658b6ef (diff) | |
IQ1_S_R4: better 1.5 bpw quants (#185)
* iq1_s_r4: basics - quantize/dequantize
* iq1_s_r4: gemm/gemv works on AVX2/Zen4
* Don't forget to make sure we have a multiple of 4 rows per thread
* iq1_s_r4: this is better
* iq1_s_r4: fix Zen4 after AVX2 changes
* iq1_s_r4: NEON gemm/gemv
* iq1_s_r4: more bits for shared experts
With this mix we arrive at PPL(512) = 9.4140
for Deepseek-Lite using 1.766 bpw for the repeating layers.
On the Ryzen-7950X we get PP-512 = 494 t/s and
TG-128 = 52 t/s @ 16 threads.
* Forgotten counter increment
* iq1_s_r4: slightly faster AVX2/Zen4 gemm/gemv
* Compiler warnings
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/quantize/quantize.cpp | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 5ffdbc84..1c847e6b 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -29,6 +29,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "IQ2_M", LLAMA_FTYPE_MOSTLY_IQ2_M, " 2.7 bpw quantization", }, { "IQ2_M_R4", LLAMA_FTYPE_MOSTLY_IQ2_M_R4, " 2.7 bpw quantization", }, { "IQ1_S", LLAMA_FTYPE_MOSTLY_IQ1_S, " 1.56 bpw quantization", }, + { "IQ1_S_R4", LLAMA_FTYPE_MOSTLY_IQ1_S_R4, " 1.5 bpw quantization", }, { "IQ1_M", LLAMA_FTYPE_MOSTLY_IQ1_M, " 1.75 bpw quantization", }, { "IQ1_BN", LLAMA_FTYPE_MOSTLY_IQ1_BN, " 1.62 bpw quantization (Bitnet)", }, { "IQ2_BN", LLAMA_FTYPE_MOSTLY_IQ2_BN, " 2.00 bpw quantization (Bitnet)", }, @@ -510,6 +511,7 @@ int main(int argc, char ** argv) { params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_S || params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XXS_R4 || params.ftype == LLAMA_FTYPE_MOSTLY_Q2_K_S || params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS_R4 || params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_S || + params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_S_R4 || params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_M)) { fprintf(stderr, "\n==========================================================================================================\n"); fprintf(stderr, "Please do not use IQ1_S, IQ1_M, IQ2_S, IQ2_XXS, IQ2_XS or Q2_K_S quantization without an importance matrix\n"); |