GitHub · Cuda
bpx03/QEngine
Fast open-source (MIT) LLM inference engine in C++/CUDA for RTX 3090-class GPUs: Qwen3.8-Flash-Next (~1,000 tok/s with 8 agents on 3x RTX 3090) and Qwen3.8-27B, OpenAI/Anthropic-compatible API.
- Stars
- 75
- Forks
- 8
- Stars gained in 24 hours
- +4
- Forks gained in 24 hours
- +2
Topics: cuda, inference, llm, openai-api, qwen, rtx-3090, speculative-decoding
Latest data point: Nov 20, 2026 · 75 stars · 8 forks