Mininglamp-AI/cider
W8A8/W4A8 inference + optimized SDPA on Apple Silicon — unlocking unused INT8 TensorOps in M5 for 1.2–1.9× faster LLM prefill, plus FlashInfer-inspired GQA decode attention for up to 1.6× SDPA speedup, built as MLX custom primitives.
358
Stars
17
Forks
36.1
Radar Score
Stable
Momentum
Scoring Breakdown
Impact46.0
Velocity27.2
Health32.6
Growth Metrics
7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Python