Supercharging Large Language Models: DEJAVU’s Inference Time Surpasses FasterTransformer by 2× | Synced
In a new paper Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time, a research team presents DEJAVU, a system that employs a cost-effective algorithm to predict contextual sparsity dy...
Source: Synced | AI Technology & Industry Review
In a new paper Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time, a research team presents DEJAVU, a system that employs a cost-effective algorithm to predict contextual sparsity dynamically for each layer, combined with an asynchronous and hardware-aware implementation to accelerate LLM inference.