Decode Context Parallelism (DCP) in vLLM shards KV cache across GPUs by sequence dimension, enabling 3× higher throughput on long-context agentic workloads compared to standard tensor parallelism.
Efficient Decode Context Parallelism with vLLM for Long Context Workloads
calendar_today
August 7, 2026
person
Seonghee Lee, Sungsoo Ha, Omri Almog (NVIDIA), Lucas Wilkinson (Red Hat AI)
domain
vllm