Tagged: bloom

4 articles

Latest

LLM.int8() Cuts BLOOM-176B Memory in Half—No Performance Loss

BLOOM hits under 1ms per token on 8 A100s, but setup is everything

How Hugging Face cut Bloom inference latency 5x and boosted throughput 50x

Open LLMs hit a wall in 2023: data scarcity, not model size, became the bottleneck