diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-07-20 10:05:23 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-20 10:05:23 +0200 |
| commit | f989fb03bd12752ad6e93717ca4bd298d5001d99 (patch) | |
| tree | 7a127aba5c05667904b7e28a46d07c2d295ef619 /gguf-py/gguf/constants.py | |
| parent | 07673c6c33753487dd054dcff37f19d93d6c56d3 (diff) | |
Adding IQ1_KT - 1.75 bpw SOTA quants (#616)
* iq1_kt: basics
* iq1_kt: CUDA dequantize
Testing with LlaMA-3.1-8B-Instruct, we get almost the same PPL
as iq2_xxs, so about 0.2 bpw fewer bits for the same quality.
* iq1_kt: CUDA MMQ
* iq1_kt: CUDA MMVQ
* iq1_kt: AVX2 GEMM/GEMV
* iq1_kt: convert/repack to q8_0_r8 (AVX2)
* iq1_kt: slightly faster GEMV
18.6 t/s -> 19.4 t/s
* iq1_kt: NEON GEMM/GEMV
Pathetic as usual
* iq1_kt: slightly faster NEON - still pathetic
* iq1_kt: tiny bit better GEMV on NEON
* iq1_kt: convert/repack to q8_0_r8 (NEON)
* iq1_kt: very slightly faster convert/repack to q8_0_r8 on NEON
* Adding frgotten file
* iq1_kt: add to constants.py
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'gguf-py/gguf/constants.py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 767637c5..32a667e2 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -1322,6 +1322,7 @@ class GGMLQuantizationType(IntEnum): IQ4_KT = 155 IQ3_KS = 156 IQ2_KL = 157 + IQ1_KT = 158 Q4_0_R8 = 202 Q5_0_R4 = 206 Q8_0_R8 = 208 @@ -1539,6 +1540,7 @@ GGML_QUANT_SIZES: dict[GGMLQuantizationType, tuple[int, int]] = { GGMLQuantizationType.IQ4_KT : ( 256, 128), GGMLQuantizationType.IQ3_KS : ( 256, 102), GGMLQuantizationType.IQ2_KL : ( 256, 86), + GGMLQuantizationType.IQ1_KT : ( 256, 56), GGMLQuantizationType.Q4_0_R8 : ( 32, 18), GGMLQuantizationType.Q5_0_R4 : ( 32, 22), GGMLQuantizationType.Q8_0_R8 : ( 32, 34), |