{"name":"hyperflare-inference","repo":"NVIDIA/hyperflare-inference","url":"https://midorreal.com/project/nvidia-flare-local-inference","repository":"https://github.com/NVIDIA/hyperflare-inference","description":"","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/NVIDIA/hyperflare-inference","checked":"22 Nov 2026"},"language":{"value":"Rust","source":"https://github.com/NVIDIA/hyperflare-inference","checked":"22 Nov 2026"},"last_release":{"value":"v0.1.0, 11 Nov 2026","source":"https://github.com/NVIDIA/hyperflare-inference/releases","checked":"22 Nov 2026"},"releases":{"value":"1","source":"https://github.com/NVIDIA/hyperflare-inference/releases","checked":"20 Nov 2026"},"contributors":{"value":"25","source":"https://github.com/NVIDIA/hyperflare-inference/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/NVIDIA/hyperflare-inference","checked":"22 Nov 2026"}},"stars":824.0,"writeup":{"what_it_is":"Flare is a local inference server for NVIDIA SM120/SM121 GPUs, aimed at long conversations, coding agents, and repeated tool use. It uses PyTorch-based tooling at build time to prepare model packages, and a Rust runtime called Helios to serve them without Python.","audience":"Users with NVIDIA SM120/SM121 workstations or compact systems such as DGX Spark","claims":[{"kind":"specific","claim":"Targets NVIDIA SM120/SM121 GPUs","excerpt":"local inference server for NVIDIA SM120/SM121 GPUs","status":"not_checked"},{"kind":"specific","claim":"Serves prepared model packages from a Rust runtime without Python","excerpt":"Helios, the Rust runtime, serves that package without Python.","status":"not_checked"},{"kind":"specific","claim":"Compilation and graph capture finish before serving","excerpt":"Compilation and graph capture finish before serving.","status":"not_checked"},{"kind":"broad","claim":"Aims to make available memory, bandwidth, and compute go further","excerpt":"Its goal is to make the memory, bandwidth, and compute in workstations and compact systems such as DGX Spark go further","status":"too_broad"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-06"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":82,"reality":80,"gap":2,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-11-11T19:31:22+00:00","text":"Latest release v0.1.0","source":"https://github.com/NVIDIA/hyperflare-inference/releases"},{"date":"2026-10-20T17:09:40+00:00","text":"Repository created","source":"https://github.com/NVIDIA/hyperflare-inference"}],"cite":"hyperflare-inference is a GitHub project at https://github.com/NVIDIA/hyperflare-inference written mainly in Rust.","attribution":"Data from Mid or Real, https://midorreal.com/project/nvidia-flare-local-inference, checked 22 November 2026. Attribution with a link is required.","still_real":null}