Sounds like just the sort of thing FGPA's were made for.
The $$$ would probably make my eyes bleed tho.
Current FPGAs would have terrible performance. We need some new architecture combining ASIC LLM perf and sparse reconfiguration support maybe.
Wouldn't it be the opposite of freezing weights?
Current FPGAs would have terrible performance. We need some new architecture combining ASIC LLM perf and sparse reconfiguration support maybe.