5 projects
swiftagents
Superfast logprob-native agent runtime
vramtop
The htop for GPU memory. Beautiful. Zero-friction. NVIDIA-first.
cacheshrink
KV Cache Compression via Multi-Head Latent Attention with Riemannian Optimization
torch-optstate
Optimizer state virtualization and compression for PyTorch
optimizeai
OptimAI is a powerful Python module designed to optimize your code by analyzing its performance and providing actionable suggestions. It leverages a large language model (LLM) to give you detailed insights and recommendations based on the profiling data collected during the execution of your code.
