LS

guqiong96/Lsglang

Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parallel architecture, suitable for MOE model hybrid inference.

52 5 +0/wk
GitHub
cpu decode gpu hybird inference model moe numa parallelism prefill sglang
Trend 3

Star & Fork Trend (16 data points)

Stars
Forks

Multi-Source Signals

Growth Velocity

guqiong96/Lsglang has +0 stars this period . 7-day velocity: 2.0%.

Deep analysis is being generated for this repository.

Signal-backed technical analysis will be available soon.

Metric Lsglang dna-memory openclaw-engram garycli
Stars 52 525252
Forks 5 13113
Weekly Growth +0 +1+0+0
Language Python PythonTypeScriptPython
Sources 1 111
License Apache-2.0 Apache-2.0MITApache-2.0

Capability Radar vs dna-memory

Lsglang
dna-memory
Maintenance Activity 100

Last code push 1 days ago.

Community Engagement 48

Fork-to-star ratio: 9.6%. Lower fork ratio may indicate passive usage.

Issue Burden 70

Issue data not yet available.

Growth Momentum 30

No measurable growth in the current period (first-day cold start expected).

License Clarity 95

Licensed under Apache-2.0. Permissive — safe for commercial use.

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