vram
4 stories and discussions about vram, aggregated from every source we track.
1.
Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data. - volotat/mini-AGI
2.
VRAM for LLMs is a bandwidth problem: every token streams the whole model from memory. Bandwidth per tier, the 20x offload cliff, and what fits in 16, 24 or 48 GB.
3.
A Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of datagithub.com
Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data. - volotat/mini-AGI
4.
Fork off LLama cpp that newly scales GPU 2x 4x etc also on big models not fully fitting in vram - neurall/llama.cpp