vLLM's Decode Context Parallelism triples long-context throughput with two flags.

DCP splits KV cache across GPUs by token position rather than attention head, eliminating the duplication that caps tensor parallelism on long contexts (vLLM). On 8×B200 with Kimi K2.6, baseline TP plateaued at ~1,863 tok/s/GPU at concurrency 64 while DCP reached 6,091 tok/s/GPU at concurrency 512 using only 82% of KV memory, staying stable past 200K-token sequences. Enable with --tensor-parallel-size N --decode-context-parallel-size M. Helps MLA/GQA models on 64K+ contexts with large-input/short-output agentic traffic, which describes basically every coding agent. Hurts on short contexts or weak GPU interconnect.