Sorry but has anyone in this thread actually tried running local LLMs on CPU? You can easily run a 7B model at varying levels of quantization (ie. 5 bit quantization) and get a generalized prompt-able LLM. Yeah, of course it’s going to take ~4GB of RAM (which is mem-mapped and paged into memory), but you can easily fine tune smaller more specific models (like the translation one mentioned above) and have surprising intelligence at a fraction of the resources.
Take, for example, phi-2 which performs as well as 13B param models but with 2.7B params. Yeah, that’s still going to take 1.5GB RAM which Firefox wouldn’t reasonably ship, but many lighter weight specialized tasks could easily use something like a fine tuned 0.3B model with quantization.
barsoap@lemm.ee 7 months ago
I don’t think any inference engines have actually been optimised to run on CPUs. You’re stuck with 32-bit floats but OTOH that just means that you can do gigantic winograd transformations with the excess precision, needing far fewer fmuladds in total and CPUs are better at dealing with the memory access patterns that come with transforming the convolution. Most people have at least around 1TFLOP of compute in their CPU (e.g. a Ryzen 3600 has that much) that’s not ever seeing the light of day. About a fifth of what an RX 570 has, it’s a difference but not a magnitude and you can run SDXL with that kind of class of card (maybe not the 570 dunno about software support but a 5500 works, despite AMD’s best efforts to cripple rocm).
Also from what I gather they’re more or less doing summarybot for your browsing history, that’s not a ChatGPT or Llama-style giant model you can talk with.
Also to all those people complaining: There’s already AI in firefox, the translation models are about 17MB per language pair, gzipped.
model_tar_gz@lemmy.world 7 months ago
ONNX Runtime is actually decently well optimized to run on CPUs; even with large models. However, the simple truth is that there’s really no escaping that Billion+parameter models need to be quantized and even pruned heavily to fit in memory and not saturate the CPU cache so inferences/generations don’t take forever. That’s a reduction in accuracy, so the quality of the generations aren’t great.
There is a lot of really interesting research and development being done right now on smart quantization and pruning. Model serving technologies are improving rapidly too—paged attention is a really cool technique for effectively leveraging tensor core hardware—I don’t think that’s supported on CPU yet but it’s probably not that far off.
It’s a really active field and there’s just as much interest in running huge models on huge hardware as there is big models on small hardware.