Author

S. Sivashanmugam

h-index 1 View on Semantic Scholar

We have 1 of 2 papers

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

Elastic KV Cache for LLM Serving:A Working Reclamation Mechanism, and Why Chunked Prefill Already Closes the Gap

The authors' elastic KV cache lends the reserve to the KV pool during decode and returns it before prefill, driven by the scheduler's one-step-ahead view of the next batch, driven by the scheduler's one-step-ahead view of the next batch.

S. Sivashanmugam · 0 citations