Hacker News new | ask | show | jobs
by storus 94 days ago
They significantly lowered latency compared to EPYC/Xeon, which is critical for streaming agents (e.g. text/audio/video agents).
1 comments
stingraycharles 94 days ago
What latency? How much is it compared to LLM inference speed?
link
storus 94 days ago
See the Redpanda comment/link here.
link