Viewing profile — smpanaro

In practice, how often do the models use the ANE? It sounds like you are optimizing for speed which in my experience always favors GPU.

For single batch inference of anything remotely LLM you'll hit the memory bound way before FLOPs, so I haven't actually looked at FLOPs much. For raw performance GPU is certainly b…

coremltools is the only way to run on ANE, so less of a trick and more of a requirement. The tricks are more around optimizing for the hardware capabilities/constraints. For instan…

What do you mean by less wide? The main bottleneck for transformers is memory bandwidth. ANE has a much lower ceiling than CPU/GPU (yes, despite unified memory). Chunking is actual…

Not a public follow-up but the iOS 17 speech-to-text model has a clever approach to KV caching that works within the ANE’s constraints (fixed size inputs). I wrote about it here[0]…

I bet these can all run on ANE. I’ve run gpt2-xl 1.5B on ANE [1] and WhisperKit [2] also runs larger models on it. The smaller ones (1.1B and below) will be usably fast and with qu…

Has perplexity fallen out of favor? I didn't see it mentioned anywhere. I tried using lm-eval for the 2B model but the results seem wrong (46.1288).

The jump was due to them fixing a bug. There’s a footnote about it on the bottom of page 5. In the Discord, they mentioned a TinyLLaMa v2, presumably that would have this bug (and …

MobileVLM [1] is another recent small multimodal model. They trained their own 1.4B/2.7B LLaMa from scratch using RedPajama and Vicuna instead of leveraging Phi-2. The papers only …

> Multi-device: Operations can run on any of the supported devices (currently, the CPU and GPU). Probably reading into this too much, but is this hinting at future Neural Engine su…

Yeah, I believe it is. You trade off speed for lower power usage and CPU. 8 tokens/sec is usable though.

You can do autoregressive decoding with KV caching on the Neural Engine. You have to make a bit of a trade off and use fixed size inputs [1] but the speed up over no caching is mea…

I've been looking at these files too and have another data point for unilm.bundle being the new text prediction. If you take an iOS simulator, turn off "Settings > General > Keyboa…

There is an input for temperature in the CPU model. If you can find and hook the call to predict you can probably see what is being passed. Interestingly the Neural Engine version …

Sorry for the confusing phrasing about STT vs TTS. I'm not familiar with cases where you would use something like this 'at the edge' instead of say a laptop. I was thinking maybe s…

What's an example use case for something like this? "At the edge" makes me think offline but are you generating audio at anything faster than real time in that case? Would be curio…

Also not an expert, but I believe it is a little bit of both for inference. If you are generating token-by-token naively, you do need to pay the n^2 cost since every token must att…