Sheared LLaMA: Accelerating Language Model Pre-Training via Structured Pruningxiamengzhou.github.io·3 pts·jmorgan·0
Efficient Memory Management for Large Language Model Serving with PagedAttentionarxiv.org·102 pts·jmorgan·16
Launch HN: Infra (YC W21) – Open-source access management for Kubernetesgithub.com·159 pts·jmorgan·58
Salesforce introduces several new developer tools including serverless functionstechcrunch.com·2 pts·jmorgan·0