Hacker News Reader

Comment by om8 | Hacker News Reader

Ternary quantization does not make any sense. Vector quantization and trellis based methods are better in this region for PTQ.

View on HN

PTQ and vector quantization aren’t used for this because part of the point of ternary LLMs is to make them faster. In a ternary LLM every weight is an add, subtract, or no-op so it is fast on CPU.

If you’re just using a code book to reconstruct a f16 model the only savings you can get are in sending it over the wire.

which is important though since sending it across the wire over and over and over is actually the main bottleneck.

Wire typically means internet connection, and it’s hardly the bottleneck

in the case of large language models, the wire is the communication of your parameters between your layers of memory that is often the bottleneck. To do a forward pass, you need to use all parameters once, and so the communication between the compute and the storage is the bottleneck, and that bottleneck is also a bunch of wires.

The other bottleneck is the amount of fast storage, which compression also improves.

> If you’re just using a code book to reconstruct a f16 model the only savings you can get are in sending it over the wire.

That’s why you need to use efficient gemm kernels like FLUTE for inference. They are ~as good as what you can do with ternary quantization.

And storing it in memory. Memory is expensive.

If you want sub-2 bit llm, get one that’s already trained in higher precision, and compress it with something like YAQA/QTIP with finetuning or PV-tuning + AQLM/HIGGS

Reply on news.ycombinator.com