Jing-Chun Gao

VPP: Virtual Pipeline Parallelism for Efficient Chunked Prefill in Long-Context LLM Inference

Chunked prefill pipeline parallelism (CPP) is a key technique for LLM inference. However, equal-size chunks exhibit imbalanced latency, as later chunks attend longer prefix KV caches and incur higher attention costs, leading to pipeline bubbles. Existing approaches mitigate this imbalance through dynamic chunk resizing...