Inkling Lands on Modal Endpoints
andersonbcdefg · x · 2026-07-16
The post shares news of Inkling's launch: the model is now available on Modal's first endpoint with token-based billing.
Two implementation details are highlighted: first, Inkling was released by @thinkymachines; second, Modal uses a custom DFlash speculator, reportedly delivering 67% higher throughput and interactivity. It currently runs on Modal Auto Endpoints using SGLang.
Related event: Modal adds Inkling to Auto Endpoints with DFlash acceleration(5 posts)→
More from Infra
- oMLX 0.5.2 adds Mac menu-bar stats, low-bit decode kernels, and faster downloads — awnihannun · 2026-07-22
- Strangeworks launches Aura to turn enterprise ops into production optimization systems — whurley · 2026-07-22
- Graph workload 854.graph500 enters SPEC CPU 2026 as a new CPU benchmark — Prof_DavidBader · 2026-07-22
- HilbertRaum open-sources a fully local AI chat and document analysis app for private use — Vladowski · 2026-07-22
- Hybrid and local inference are emerging as a response to AI energy and token costs — dmitry140 · 2026-07-22
- NVIDIA details Vera CPU with 2x performance claims and a 22,000-core rack — ryanshrout · 2026-07-22