turboquant-vllm by Alberto-Codes

Native Windows vLLM 0.26.0: CPython 3.13, CUDA 12.8, SM 7.5/8.6/8.9/12.0 for RTX 20/30/40/50, OpenAI-compatible serving, Triton/FlashAttention, 10 KV-cache formats, Multi-TurboQuant, and experimental CPU/RAM/NVMe prompt-KV offload. No WSL or Docker. Maintained by aivrar on GitHub, where it has earned 36 stars from the community.

This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference speed. Maintained by TheToughCrane on GitHub, where it has earned 71 stars from the community.

Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated. Maintained by jagmarques on GitHub, where it has earned 24 stars from the community.