Tag
A writeup of a multi-stage LLM pipeline that fetches newsletter articles, summarizes, de-duplicates, scores importance and urgency, and publishes a digest, with robust prompt-injection defenses and self-validation.
ProxyKV is a cross-model proxy pruning framework that offloads importance scoring to a lightweight small model, achieving high precision KV cache pruning with much lower prefilling overhead, matching KVZip accuracy across Llama-3.1, Qwen-2.5, and Qwen-3 families.