A throughput-oriented high-performance serving framework for LLMs

Advanced Topics on Systems for X

Serving multiple LoRA finetuned LLM as one

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 17+ clouds, or on-prem).

FSCQ is a certified file system written and proven in Coq

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

The Firmament cluster scheduling platform

Coz: Causal Profiling

Read-Log-Update: A Lightweight Synchronization Mechanism for Concurrent Programming