Viewing profile — punkgenius

This seems to be more achievable and cost-effective than Cerebras. Some comments mention Cerebras cost millions for each 'die'.

I think it’s all about the performance-to-cost ratio. The reason you need a cache is because you want to reduce the latency and power accessing data. DRAM can also be thought of as…

Nowadays GPUs have sacrificed some performance for better programmability. ASICs always trade programmability for better performance and energy efficiency, it's really about how 's…

Maybe 74 tflops is the best they've achieved, but not all 16 GPUs can consistently hit that number? Just guessing.. The 211 tokens/sec throughput on GPU is just insane, it's even b…

Looks like figure 8 of paper [1] says it is 18 tokens/s

~200MB to 1GB per ASIC, from Table 2 on page 10.