Author

Sandeep Kumar

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

QEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decoding

QEvict is proposed, a three-tier KV-cache management scheme that replaces binary retain-or-delete eviction with recoverable eviction, and maintains high-confidence windows in full precision, stores intermediate windows in a quantized recoverable tier, and deletes only the lowest-confidence windows.

Ayushman Garg, Akshita Gupta, Shaswata Bhattacharya et al. · 1 citation