Voxlap GPU port streams near-real-time on an L40S via CUDA Rust port
idanbeck · x · 2026-10-02
Following gavanw's GPU port of voxlap, idanbeck ported it to CUDA Rust and ran it on his own inference system, achieving near-real-time streaming from an L40S. He says it works "super well" and will share a proper video later.
Related event: Dev ports classic Voxlap engine to GPU with Claude in hours(3 posts)→
More from coding & agent
- Dev lets Sol Ultra improve his engine for 2 hours — usage barely moved 2% — Dimillian · 2026-10-02
- Meme: Developers hitting 'Allow' in Claude Code over and over — aishashok14 · 2026-10-02
- Microsoft's Autopilot isn't Scout 2.0: a private-preview shift to a Foundry-hosted cloud agent platform — pswider · 2026-10-02
- Researcher uses MiniMax M3 to build PoC, lands CVSS 8.8 memory-corruption CVE in Ghost — DanielLockyer · 2026-10-02
- Opus 5.5 puts Minecraft into Slime Rancher and it actually works — Angaisb_ · 2026-10-02
- Harness engineering explained: building the scaffolding around coding agents — tekbog · 2026-10-02