SPECTRA lets LLMs squeeze KV caches past the 2‑bit wall, unlocking up to 12× memory savings
SPECTRA re‑orients the KV cache into a data‑driven spectral basis and pours bits into the few informative channels. On Llama‑3.1‑8B and Qwen2.5‑7B it delivers near‑lossless 4× compression, stays usable at 8×, and even reaches 12×, letting the same GPU handle much longer contexts.