Skip to content

Achieve Truly Serverless GPUs With libfuse, CRIU, and CUDA-Checkpoint#

GTC 2026 digest Program Wildcard pick San Jose · 16–19 March 2026

Abstract Talk page Slides Recording

Charles Frye (Modal) — Talk, Tuesday, March 17

  • Why: Serverless inference only works if GPU containers boot fast — and the checkpoint/restore mash (CRIU + CUDA-Checkpoint + libfuse) used to get there is genuinely novel systems work the PM wouldn't naturally search for.
  • What: The techniques Modal developed to speed up GPU container boots and achieve truly serverless execution for workloads across thousands of GPUs. (from abstract only)
  • How: Process checkpoint/restore via CRIU combined with CUDA-Checkpoint for GPU state and libfuse for filesystem setup — the abstract names the tools but not the measured boot-time gains.
  • Where applicable: Modal's platform at thousands-of-GPUs scale; the techniques generalize to any system that needs fast cold-start of GPU replicas.