Skip to content
Made with Jev

GitHub · by Eric Zhang

openjev-sglang

A public Jev-compatible API on an open model: 64 tasks in under a second.

Eric Zhang on X

Eric Zhang

@ekzhang1

Inspired by @typesafeai , here is a Jev-compatible public API to play with It runs a comparable open model (Qwen3.6-35B-A3B), and just uses SGLang radix cache to preserve the prefill reuse / really fast parallel systemone generation - 64 tasks in <1s. github.com/ekzhang/openje…

Video from @ekzhang1

Sep 17, 2026 · 984 likesOpen on X

Eric Zhang published a Jev-compatible API to play with. It runs an open model, Qwen3.6-35B-A3B, and uses the SGLang radix cache to reuse the prefill across parallel questions. He reports 64 tasks in under a second.

ekzhang/openjev-sglang on GitHub

Stars
333
Forks
46
Language
Python
Last push
Oct 1, 2026

Repository created Sep 17, 2026. Counts read from the GitHub API on Oct 15, 2026, and they move daily — quote them with the date.

Open the source

More like this