GitHub · C++
gittensor-ai-lab/sparkinfer
Fastest MoE/LLM inference runtime for consumer and edge Blackwell GPUs. SN74 on Gittensor.
- Stars
- 93
- Forks
- 82
- Stars gained in 24 hours
- +3
- Forks gained in 24 hours
- 0
Topics: agentic-ai, bittensor, blackwell, cuda, edge-ai, gittensor, gpu, gpu-programming, inference-engine, kernel-optimization
Latest data point: Nov 22, 2026 · 93 stars · 82 forks