Static landing page for RustFS GPUCache.
GPUCache offloads KV cache for LLM inference onto BlueField DPUs and NVMe flash, giving GPU clusters a shared L4 context-memory tier.
index.html— page markupstyles.css— visual system and responsive layoutscript.js— reveal animation and screenshot helperdesign-tokens.md— local design constraints used for this prototype
Open index.html directly in a browser, or run a simple static server:
python3 -m http.server 8080Then visit http://localhost:8080.