Pinned
dstack
@dstackai
Control plane for agents & engineers to provision compute and run training & inference across NVIDIA, AMD, and other chips — on clouds, Kubernetes, and on-prem.
dstack 0.21.1 is out! Presets: the inference optimization agent can now patch source code (serving framework, kernels, etc). Also, sessions can be linked, so each new one starts from the previous best and pushes further. Gateways: replicas are now fault tolerant and support- GPU builders, inference engineers, and training teams are meeting in SF on July 23. Join engineers @aiand_ @NVIDIAAI, @ByteDanceOSS, @radixark, @liquidai, @zml_ai, @GraphsignalAI, Cosmic Labs, Kernelize, and more for an evening of lightning talks and networking. Hosted by
- dstack 0.20.28 is out 🚀 • Agent-driven optimization of inference endpoints for a given model and hardware • Use the dstack CLI/API from inside runs • Export server telemetry via OpenTelemetry • Use @vast_ai spot instances github.com/dstackai/dstac…I’m incredibly excited to release endpoint presets, our first step toward fully agentic inference optimization in @dstackai. The goal is simple: optimized inference performance for any model on any hardware. Our first batch of presets and benchmarks is coming soon! Let us know
- Working on GPUs, inference, or training? Come hang out with us in SF on July 23. We’re bringing together engineers from @NVIDIAAI, @ByteDanceOSS, @radixark, @liquidai, @zml_ai, @GraphsignalAI, Cosmic Labs, Kernelize and more for lightning talks and networking. Organized by
