Recent Blog Posts

• LEAP: Learnable End-to-End Adaptive Pruning of LLMs
• When Quantization Isn’t Enough: Why 2:4 Sparsity Matters (PyTorch Blog)
• BEAM: Blockwise Error Minimization for One-shot Compression of LLMs
• More posts coming soon...

Related Repositories

• LEAP GitHub
• PATCH GitHub
• SLiM GitHub
• SLoPe GitHub
• MKOR GitHub
• BEAM GitHub

Navigation

• About Me