G github.com Show HN: Standalone TurboQuant KV Cache Inference Implements TurboQuant (ICLR 2026, arXiv:2504.19874) KV cache compression directly inside a Transformers inference script. All algorithms are self-contained. Minimal dependencies.- uses https://huggingface.co/g023/Qwen3-1.77B-g023 as the demonstration model (throw model files in Qwen3-BEST folder) 3 points g023 7 months ago 4 comments
- uses https://huggingface.co/g023/Qwen3-1.77B-g023 as the demonstration model (throw model files in Qwen3-BEST folder)