SubQ Snap hits 11.4B tokens/hr within 3 hours of launch on SkyPilot infrastructure
skypilot_org · x · 2026-10-13
Subquadratic launched SubQ Snap, served on SkyPilot's GPU clusters, reaching 11.4B tokens/hr (nearly 7B in the last half hour) within the first three hours via custom routing and inference optimizations tuned for long context. The team notes possible latency spikes and is considering opening some training clusters for inference.
More from Infra
- Only 8% of cloud vendors support OIDC — dev calls to kill long-lived API keys — cramforce · 2026-10-23
- Swift-1.5-Qwen3.8-27B ported to hipfire MQ4: 2.2x faster end-to-end than GGUF on a 7900 XT — Queasy_Asparagus69 · 2026-10-23
- Intel CTO: chip output can at best 2X while AI compute grows 3X per year — SammaVaco · 2026-10-23
- Engineer reverse-engineers projector TV's 10s wake lag to a cold-booting Linux board — banteg · 2026-10-23
- Ollama CEO says enterprise AI is having its PC moment on This Week in AI — ollama · 2026-10-23
- Modal open-sources Spindle, a Tinker-compatible training server that charges GPU time instead of tokens — josh_wills · 2026-10-23