research
∙
05/16/2023
SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification
The high computational and memory requirements of generative large langu...
share
research
∙
02/04/2022
Direct Telemetry Access
The emergence of programmable switches allows operators to collect a vas...
research
∙
10/11/2021