parallel-decoding

Here is 1 public repository matching this topic...

JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.

cuda inference game-ai structured-output llm vllm parallel-decoding jev

To associate your repository with the parallel-decoding topic, visit your repo's landing page and select "manage topics."