openjev-sglang A server implementing the TypeSafe/Jev HTTP API with Qwen3.6-35B-A3B on SGLang. Each container one B200 with SGLang 0.5.19's Rust frontend, radix caching, and breakable prefill CUDA graphs. A separate Python API process uses FastAPI, uvloop, the Rust-backed HF tokenizer, and pooled asynchronous HTTP connections to SGLang on localhost. CUDA dependencies stay in SGLang's container; on your laptop installs only the API, deployment tools, and tests. Run on Modal The deployment prints a URL. It uses a Modal Server, , , and .
| Stars | 333 |
| Forks | 46 |
| Language | Python |
| Category | AI Tool |
| Quality Score | 66.269155881763/100 |
| Open Issues | 5 |
| Last Updated | 2026-10-01 |
| Created | 2026-09-17 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with openjev-sglang for enhanced workflows:
Explore other popular ai tool tools:
openjev-sglang is Jev-compatible API endpoint based on open models (prefill-only). It is categorized as a AI Tool with 333 GitHub stars.
openjev-sglang is primarily written in Python. It covers topics such as jev, llm, structured-generation.
You can find installation instructions and usage details in the openjev-sglang GitHub repository at github.com/ekzhang/openjev-sglang. The project has 333 stars and 46 forks, indicating an active community.