MI

psmarter/mini-infer

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

161 8 +5/wk
GitHub
continuous-batching cuda inference inference-engine kv-cache language-model llm machine-learning moe pagedattention pytorch quantization
Trend 3

Star & Fork Trend (21 data points)

Stars
Forks

Multi-Source Signals

Growth Velocity

psmarter/mini-infer has +5 stars this period . 7-day velocity: 3.2%.

Deep analysis is being generated for this repository.

Signal-backed technical analysis will be available soon.

Metric mini-infer elastic_transformers AudioMuse-AI-NV-plugin aidevops
Stars 161 161161162
Forks 8 24439
Weekly Growth +5 +0+0+0
Language Python Jupyter NotebookGoShell
Sources 1 111
License MIT Apache-2.0AGPL-3.0MIT

Capability Radar vs elastic_transformers

mini-infer
elastic_transformers
Maintenance Activity 100

Last code push 0 days ago.

Community Engagement 70

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

Issue Burden 70

Issue data not yet available.

Growth Momentum 100

+5 stars this period — 3.11% 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.