✉news TechnologyAI first seen 9 h ago, last 9 h ago, peak #37
UC Berkeley and FuriosaAI Propose HBF for LLM Serving
Original: HBF for High-Throughput LLM Serving (UC Berkeley, FuriosaAI)
Researchers at UC Berkeley, working with chipmaker FuriosaAI, have published work on HBF, a memory approach aimed at high-throughput serving of large language models. The piece, carried by Semiconductor Engineering, focuses on how new memory architectures could ease the bandwidth and cost bottlenecks that limit LLM inference at scale. The work is being followed by readers tracking hardware innovation for AI infrastructure.
Why now: Interest in new memory and hardware approaches that can reduce the cost of running large language models is high amid the AI infrastructure boom.
UC BerkeleyFuriosaAISemiconductor EngineeringHBF
Evidence
- HBF for High-Throughput LLM Serving (UC Berkeley, FuriosaAI) · Semiconductor Engineering
API: https://socialmediatrends-api.osmike.com/v1/trends/792627