GitHub · Rust
avifenesh/memra
Memra is a Rust + CUDA LLM inference engine with hand-written kernels, NVFP4 and mixed-precision execution, and correctness gates scoped to each model and GPU
- Stars
- 7
- Forks
- 1
- Stars gained in 24 hours
- +1
- Forks gained in 24 hours
- 0
Topics: ai, blackwell, cuda, deepseek, dflash2, dgx-spark, gguf, glm, inference, inference-engine
Latest data point: Nov 20, 2026 · 7 stars · 1 forks