Taalas HC1: 17,000 tokens/sec on Llama 3.1 8B vs Nvidia H200’s 233 tokens/sec. 73x faster at one-tenth the power. Each chip runs ONE model, hardwired into the transistors.
Taalas HC1: 17,000 tokens/sec on Llama 3.1 8B vs Nvidia H200’s 233 tokens/sec. 73x faster at one-tenth the power. Each chip runs ONE model, hardwired into the transistors.
If you add levels of indirection, extra transistors and such, it would be surprising to manage to maintain the same level of performance, especially since this design seems to rely on hardwiring to achieve its speed…
Pretty sure the advantage is the AI directly on the chip.
Now it’s your proposal’s turn not to make any sense. This is an article about a chip with a hardwired model being super fast.
Of course the hardwiring is inflexible, and much, much faster.
I just think you want to argue