# Prefill Context Parallelism

Serving GLM-5.3's long contexts on 16 H200s runs into two limits: KV cache memory and prefill speed. On the prefill side, each prompt is split across eight GPUs by token (PCP) and the KV cache is sharded by token (DCP), so a 1M-token request needs only 6.7 GiB per GPU; on the decode side, Hybrid HiSparse keeps KV in host memory. On the AgentX benchmark, PCP8 × DCP8 prefill with HiSparse decode gives 1.7–3.2× the per-user speed of a DP8 deployment at the same throughput, and it is the only tested configuration that serves 1M-token contexts.

Serving GLM-5.3's long contexts on 16 H200s runs into two limits: KV cache memory and prefill speed. On the prefill side, each prompt is split across eight GPUs by token (PCP) and the KV cache is sharded by token (DCP), so a 1M-token request needs only 6.7 GiB per GPU; on the decode side, Hybrid HiSparse keeps KV in host memory. On the AgentX benchmark, PCP8 × DCP8 prefill with HiSparse decode gives 1.7–3.2× the per-user speed of a DP8 deployment at the same throughput, and it is the only tested configuration that serves 1M-token contexts.