A high-throughput and memory-efficient inference and serving engine for LLMs
Find trending repositories by name or description.
A high-throughput and memory-efficient inference and serving engine for LLMs
Fast and memory-efficient exact attention
ngx_mruby - A Fast and Memory-Efficient Web Server Extension Mechanism Using Scripting Language mruby for nginx
Fast and memory-efficient radial basis function (RBF) interpolation
A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mind.
Fast, memory-efficient self-hosted GitHub Actions cache server written in Rust. Drop-in replacement for the official cache, works with actions/cache unchanged. Supports S3, GCS, Azure Blob or filesystem storage with SQLite, Postgres or MySQL.
Trainable fast and memory-efficient sparse attention
Fast and memory-efficient classical machine learning operators