Hands-on, source-level studies of vLLM internals — reading the latest main and turning findings into upstream contributions.
vLLM Lab collects deep, contribution-oriented studies of vLLM subsystems, focused on the moving frontier.
How the native OffloadingConnector became a hybrid-aware, multi-tier subsystem, with a timeline, open issues, and two contribution scaffolds.
Reproducing the cuFile NVMe secondary-tier scaffold on H100/H200, measured against the filesystem tier.