I added that because people started attacking me since it was a bit angrier at first (the angry version was the only one) and they didn't want to send to colleagues or anyone else, just close friends so they asked me to add a smoother version and to say it's a joke
Memory capacity on the WSE is the same as before, but access to off-wafer memory is much slower, so the sweet spot is a given fixed balance of memory and compute. They have announced a partnership with AMD in which CPU/GPU hardware is used for part of the workload and the WSE-3 machines are used for inference for specialized smaller models, but I'm not really sure of the details on that.
And there is, of course, the educated guesses about what WSE-4 will be, one being adding a LOT of stacked SRAM or DRAM to tip the balance towards memory (which could also be done by having a few different tile designs with various configurations of compute and memory capacity). I am curious about which way they'll go.
Heroic effort, sifting through that code I mean, but frankly I would have started a new one from scratch, the only thing of value is the name/popularity of the original project.
Yeah, skipped most of them since they where clearly AI generated. I wonder if the authors expect that people will actually read their slop in the replies.
I will stop here, sorry but I think we have limited time to listen to opinions and nowadays since they are abundant on social media we should give preference to the substantiated ones.
