Pinned Repositories
cmu-catalyst.github.io
collage
System for automated integration of deep learning backends.
FlexFlow
A distributed deep learning framework that supports flexible parallelization strategies.
GradSign
Code for paper GradSign: Model Performance Inference with Theoretical Insights
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
cmu-catalyst's Repositories
cmu-catalyst/collage
System for automated integration of deep learning backends.
cmu-catalyst/GradSign
Code for paper GradSign: Model Performance Inference with Theoretical Insights
cmu-catalyst/cmu-catalyst.github.io
cmu-catalyst/FlexFlow
A distributed deep learning framework that supports flexible parallelization strategies.
cmu-catalyst/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs