Live data from Hacker News

Cerebras Inference: AI at Instant Speed

cerebras.ai

61–70 of 75 posts

Re: Cerebras Inference: AI at Instant Speed

#61

70b runs on 4x CS-3 estimated at $2-3m each, let’s say total system cost $10m, drawing ~100kW power. They don’t mention batch size, so let’s start with batch size 1 and see where we get. At 100% utilisation for 3 years that’d be 42 billion tokens for a cost of $10m capital plus ~$0.5m power and cooling let’s say, or $250 per million tokens. They’re claiming they can sell their API access at $0.60/million. To break ev…

your estimate of $2-3M per CS-3 is a price not a cost. It costs about $20K per wafer from TSMC and the price they charge reflects the NRE of designing the system and taping out the masks more than the additional costs to package up their wafers into a system. If this business scales, they can probably afford to lower the price by a factor of 10.

My math (and google) shows a 300 mm diameter wafer, and 300,000,000 transistors/mm^2

So for $20,000 (in quantity) you get somewhere around 10 trillion transistors?

That's enough for about 50 4096x4096 multiply-accumulate chips. At a nice slow 1 Mhz clock rate, each would take about 3.5 watts, and give you 16 teraflops of performance. If you stepped up the power and cooling, you could likely get to 350 watts of power at 100 Mhz, and 1.6 Petaflops.

50 of those chips, for $20,000 --> $400 each

Re: Cerebras Inference: AI at Instant Speed

#62
post #46

It’s insanely fast. Here’s an AI voice assistant I built that uses it: https://cerebras.vercel.app

This is pretty amazing. It's fast enough to converse with, and I can interrupt the model.

The underlying model is not voice trained -- she says things like "asterisk one" (reading out point form) -- but this is a great preview for when ChatGPT GAs their Voice Mode.

Re: Cerebras Inference: AI at Instant Speed

#63
post #46

It’s insanely fast. Here’s an AI voice assistant I built that uses it: https://cerebras.vercel.app

Fantastic demo. Do you know what's the difference between your stack and the livekit demo? [1] it shows your voice as text so you can see when you have to correct it.

Llama3 with ears just dropped (direct voice token input) which should be awesome with cerebras [2]

[1]: https://kitt.livekit.io [2]: https://homebrew.ltd/blog/llama3-just-got-ears

Re: Cerebras Inference: AI at Instant Speed

#64
post #51

70b runs on 4x CS-3 estimated at $2-3m each, let’s say total system cost $10m, drawing ~100kW power. They don’t mention batch size, so let’s start with batch size 1 and see where we get. At 100% utilisation for 3 years that’d be 42 billion tokens for a cost of $10m capital plus ~$0.5m power and cooling let’s say, or $250 per million tokens. They’re claiming they can sell their API access at $0.60/million. To break ev…

batch size by Q4 will be solid double digits (cerebras employee)

Is that e.g. batch 16/32 for each operation e.g. 16-row matmuls in a pipeline? Or a pipeline of vector-math ops that has 16/32 stages? Is the pipeline also double digits deep?

Re: Cerebras Inference: AI at Instant Speed

#66
post #10

I want to know what the current power requirements are, as well as the cost for the machine. The last time I looked at one of these it was an absolute beast (although very impressive).

They never made the price public as far as I know but said something like "less than a house". It's going to be something on the order of $300k.

Re: Cerebras Inference: AI at Instant Speed

#67
post #2

This is where we always assumed the industry was going. Expensive GPUs are great for training, but inference is getting so optimized that it will run on smaller and/or cheaper processors (per token).

Cerebras' Wafer Scale Engine is the opposite of small and cheap. https://cerebras.ai/product-chip/

Maybe the real trend is that huge parameter counts are curiosities.

Re: Cerebras Inference: AI at Instant Speed

#68

>Cerebras is the only platform to enable instant responses at a blistering 450 tokens/sec. All this is achieved using native 16-bit weights for the model, ensuring the highest accuracy responses. As near as I can tell, from the model card[1], the majority of the math for this model is 4096x4096 multiply-accumulates. So, there should be 70b/16m about 4000 of these in the Llama3-70B model. A 16x16 multiplier is about 9…

>There are enough transistors, and enough RAM on the wafer to fit the entire model.

Not the entire 70b fp16 model. It'd take 148GB of RAM to hold the entire model. Each Cerebras wafer chip has 44GB of SRAM. You need 4 of them chained together to hold the entire model.

Re: Cerebras Inference: AI at Instant Speed

#69
Q: so apparently allowing LLMs to “think” by asking it to walk through and generate preamble tokens to an answer improves quality. With this kind of speedup would it be practical/effective to achieve better output quality by baking in a “thinking” step to every prompt? Say, a few thousand tokens before the actual reply.

Re: Cerebras Inference: AI at Instant Speed

#70
> Thus to generate a 100 words a second requires moving the model 100 times per second – requiring vast amounts of memory bandwidth.

It's actually worse for the majority of GPU implementations for large models. The matrices don't fit shared memory so the model is loaded many, many times to shared memory (as tiles). Also, unless you are using Hopper distributed shared memory, CTAs can't even share across them.

It would be nice to see a Cerebras solution for pre-training and fine-tuning.

Post reply on HN