MI

psmarter/mini-infer

LLM inference engine from scratch — paged KV cache, continuous batching, chunked prefill, prefix caching, speculative decoding, CUDA graph, tensor parallelism, MoE expert parallelism, OpenAI-compatible serving

160 8 +4/wk
GitHub
continuous-batching cuda inference inference-engine kv-cache language-model llm machine-learning moe pagedattention pytorch quantization
Trend 3

Star & Fork Trend (20 data points)

Stars
Forks

Multi-Source Signals

Growth Velocity

psmarter/mini-infer has +4 stars this period . 7-day velocity: 2.6%.

Deep analysis is being generated for this repository.

Signal-backed technical analysis will be available soon.

Metric mini-infer FinSight elastic_transformers EvolutionaryForest
Stars 160 160161159
Forks 8 412434
Weekly Growth +4 +1+0+0
Language Python Jupyter NotebookJupyter NotebookPython
Sources 1 111
License MIT GPL-3.0Apache-2.0LGPL-3.0

Capability Radar vs FinSight

mini-infer
FinSight
Maintenance Activity 97

Last code push 12 days ago.

Community Engagement 25

Fork-to-star ratio: 5.0%. Lower fork ratio may indicate passive usage.

Issue Burden 70

Issue data not yet available.

Growth Momentum 100

+4 stars this period — 2.50% growth rate.

License Clarity 95

Licensed under MIT. Permissive — safe for commercial use.

Risk scores are computed from real-time repository data. Higher scores indicate healthier metrics.