diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-15 09:54:21 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-15 09:54:21 +0100 |
| commit | 85c5a1a99569ccc00c280835fe3a69b4af02c43b (patch) | |
| tree | da421487d5ddd0467b2bfd6cbbfb2666406c46f1 /examples/quantize/quantize.cpp | |
| parent | 20758edcae65213b2f575b6d23dfea67ad9dd0e0 (diff) | |
BF16_R16 - 16 interleaved bf16 rows (#142)
* Not working bf16_r4
* Adding bf16_r8
Small performance gain compared to bf16 - 258 t/s vs 234 t/s.
I guess, this is still sub-obtimal.
* bf16_rx: Very slightly faster by interleaving 16 rows
258 t/s -> 263 t/s
* Rename bf16_r4 to bf16_r16
We are interleaving 16 rows now.
* Cleanup unused stuff
---------
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 0f906b83..5e5dd7c0 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -77,6 +77,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "Q4_0_8_8", LLAMA_FTYPE_MOSTLY_Q4_0_8_8, " 4.34G, +0.4685 ppl @ Llama-3-8B", }, { "F16", LLAMA_FTYPE_MOSTLY_F16, "14.00G, -0.0020 ppl @ Mistral-7B", }, { "BF16", LLAMA_FTYPE_MOSTLY_BF16, "14.00G, -0.0050 ppl @ Mistral-7B", }, + { "BF16_R16", LLAMA_FTYPE_MOSTLY_BF16_R16, "14.00G, -0.0050 ppl @ Mistral-7B", }, { "F32", LLAMA_FTYPE_ALL_F32, "26.00G @ 7B", }, // Note: Ensure COPY comes after F32 to avoid ftype 0 from matching. { "COPY", LLAMA_FTYPE_ALL_F32, "only copy tensors, no quantizing", }, |