SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression
$ git clone https://github.com/Dynamis-Labs/spectralquant.git▲ +32 ★ this week
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
▲ +7 ★ this week
LLM KV cache compression made easy
[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
PyTorch library for cost-effective, fast and easy serving of MoE models.
Python library for designing and training your own Diffusion Models with PyTorch
ExtremeBERT is a toolkit that accelerates the pretraining of customized language models on customized datasets, described in the paper “ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT”.
Data from GitHub · snapshot Nov 13, 2026