diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-07-14 18:55:08 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-14 18:55:08 +0200 |
| commit | 45fae1a14444622478774f9a417e1d417af1ca46 (patch) | |
| tree | 2609ef06be5640749834d4fc691446771ab29f42 /gguf-py/gguf/constants.py | |
| parent | f5353047ef461e6fc9d527e09a06c9802c699929 (diff) | |
Adding IQ2_KL (#602)
* Experiments for 2.6875 bpw quants
At least according to rmse, this is significantly better than
q2_K, while using only 1/16 more bits per weight.
* iq2_kl: basics
* iq2_kl: CUDA dequantize
* iq2_kl: small improvement in PPL
Also check the two neighbouring values for the block scale
and use the one that minimizes RMSE.
* iq2_kl: MMQ
Quite good: PP-512(L3-8B) = 8472 t/s.
* iq2_kl: MMVQ
We get PP-128(L3-8B) = 162 t/s.
Which means that this is not quite as good as it should be as
(almost) same bpq q2_K is at 170 t/s.
* iq2_kl: Zen4 GEMM/GEMV
Not particularly fast. I may need to think about rearranging the bits.
* iq2_kl: better Zen4
* iq2_kl: convert/repack to q8_k_r8 (AVX2)
* iq2_kl: AVX2 GEMM/GEMV
* iq2_kl: WIP NEON
The compiler started crashing!!!
* iq2_kl: NEON
Had to work around a compiler crash when using vzip2q_u8 using
vqtbl2q_u8.
* iq2_kl: convert/repack to q8_k_r8 (NEON)
* iq2_kl: Metal dequantize
* iq2_kl: Metal GEMV - pretty slow
* iq2_kl: Metal GEMV - slightly better (40 t/s -> 44.5 t/s)
* iq2_kl: Metal GEMV - slightly better (44.5 t/s -> 46.5 t/s)
* iq2_kl: Metal GEMV - slightly better (46.5 t/s -> 47.2 t/s)
* iq2_kl: slightly better Metal dequantize
PP-512 goes to 476 t/s up from 466 t/s.
* iq2_kl: slightly better Metal dequantize
PP-512 goes to 492 t/s up from 476 t/s.
* Add iq2_kl 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 0fe3ed35..767637c5 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -1321,6 +1321,7 @@ class GGMLQuantizationType(IntEnum): IQ3_KT = 154 IQ4_KT = 155 IQ3_KS = 156 + IQ2_KL = 157 Q4_0_R8 = 202 Q5_0_R4 = 206 Q8_0_R8 = 208 @@ -1537,6 +1538,7 @@ GGML_QUANT_SIZES: dict[GGMLQuantizationType, tuple[int, int]] = { GGMLQuantizationType.IQ3_KT : ( 256, 100), GGMLQuantizationType.IQ4_KT : ( 256, 128), GGMLQuantizationType.IQ3_KS : ( 256, 102), + GGMLQuantizationType.IQ2_KL : ( 256, 86), GGMLQuantizationType.Q4_0_R8 : ( 32, 18), GGMLQuantizationType.Q5_0_R4 : ( 32, 22), GGMLQuantizationType.Q8_0_R8 : ( 32, 34), |