Repo · SDKs & integrations

Open Jev Fast

A faster inference backend for Open-Jev's local server: same request format and same 27B bf16 weights, but the forward pass is replaced by…

Open github.com ↗

From the repository

Faster inference backend for Open-Jev-27B: fused CUDA kernels, prefix tree, CUDA Graphs (B300, bf16)

How builders describe it

A faster inference backend for Open-Jev's local server: same request format and same 27B bf16 weights, but the forward pass is replaced by hand-written CUDA kernels, a prefix tree and CUDA Graphs. Needs an existing Open-Jev install and the model weights.

The decision Jev makes

Any Jev question: yes or no, a choice, or a score, from your own stack.

Where it fits

Official and community SDKs, MCP servers and integrations for calling Jev from the languages and tools you already use. All 625 sdks & integrations projects →

Related projects