GitHub · JavaScript
kikoncuo/jevfire
JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.
- Stars
- 77
- Forks
- 9
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: cuda, game-ai, inference, jev, llm, parallel-decoding, structured-output, vllm
Latest data point: Nov 22, 2026 · 77 stars · 9 forks