Kawrakow a10ccd65f3 New SOTA quantization: 4.25 bpw IQ4_KS (#83) ...

* iq4_k_xxs: basics

* WIP + adding iq3_kl quantization mix

* iq4_xxs: this looks very viable compared to iq4_xs

At the same 4.25 bpw PPL is always better, for some models
significantly better. I'll rename to iq4_ks and keep it.

* iq4_xxs: CUDA dot product

We get TG-128 = 126 t/s for LLaMA-3.1-8B, compared to 123 t/s for q4_0.

* iq4_xxs: scalar CPU dot product

Also fix the breakage I caused with the dedicated work buffer
quantization portion when the multiplication is not done
via iqk_mul_mat.

* iq4_xxs: Zen4

I noticed that iq4_xs is wrong on Zen4 (and possibly AVX2).
Again the same mistake of packing int32_t back to int16_t,
which overflows occasionally (just occasionally, that's why the
result doesn't look completely wrong, so I didn't notice).

* Fix iq4_xs (Zen4)

* iq4_xxs: AVX2

* iq4_xxs: ARM_NEON

* iq4_xxs: Metal

* iq4_xxs: slightly faster TG on Metal

* iq4_xxs: rename to iq4_ks

After all, tt is a smaller variant of iq4_k.

* iq3_kl: use iq4_ks instead of iq4_k/iq4_xs

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2024-10-09 12:54:40 +03:00

..

llama.h

New SOTA quantization: 4.25 bpw IQ4_KS (#83)

2024-10-09 12:54:40 +03:00