#kv-cache

2 posts

GLM-5.3 Optimizations, Part 2: PCP, DCP, and Hybrid HiSparse on 16 H200s

Oct 23, 2026·13 min read

vLLM serves GLM-5.3 on 16 H200s with PCP and DCP prefill and Hybrid HiSparse decode, reaching 1M-token contexts and 1.7–3.2× the per-user speed of data-parallel P/D on the AgentX agentic benchmark.

GLM 5.3 Optimizations, Part 1: Hybrid HiSparse Offloading in vLLM

Sep 8, 2026·11 min read

vLLM integrates HiSparse as a pressure-driven memory tier that composes with the Hybrid Memory Allocator and KV offloading, letting GLM 5.3 requests keep decoding when their KV no longer fits in GPU memory, so concurrency stays high.