Elon Musk
@O42nl @kirillgroshkov Tesla does INT8 inference. Way more efficient than FP16, but took us a lot of effort to overcome quantization errors.
Captured source text. Text source.
Original content from X / Twitter. If unavailable, open the original link below.
Source IDs: aryansingh0909/elon-musk-tweets-updated-daily, dadalyndell/elon-musk-tweets-2010-to-2025-march. Date precision: millisecond. Coverage details.