Loading...
Loading...
Available on 1 platform
Sign in to view source links and access this dataset
Trained TCQ codebooks enable KV cache compression at 2-3 bits per parameter, as presented in the paper 'Closing the Gap: Trellis-Coded Quantization for KV Cache at 2-3 Bits'. The dataset was created by authors buun and Claude (Anthropic) from Anthropic and was last updated in April 2026. It includes the quantization codebooks, training scripts, and the associated research paper.
Primary content is specialized codebooks and scripts for a specific quantization technique; not a traditional tabular or labeled dataset for direct model training.