guqiong96/Lvllm
LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parallel and NUMA parallel architecture, supporting hybrid inference for MOE large models.
Star & Fork Trend (15 data points)
Multi-Source Signals
Growth Velocity
guqiong96/Lvllm has +1 stars this period . 7-day velocity: 1.6%.
Deep analysis is being generated for this repository.
Signal-backed technical analysis will be available soon.
| Metric | Lvllm | ai-legal-compliance-assistant | cymbal-air-toolbox-demo | hud-python |
|---|---|---|---|---|
| Stars | 317 | 319 | 321 | 312 |
| Forks | 30 | 43 | 114 | 54 |
| Weekly Growth | +1 | +0 | +0 | -7 |
| Language | Python | Python | Python | Python |
| Sources | 1 | 1 | 1 | 1 |
| License | Apache-2.0 | N/A | Apache-2.0 | MIT |
Capability Radar vs ai-legal-compliance-assistant
Last code push 1 days ago.
Fork-to-star ratio: 9.5%. Lower fork ratio may indicate passive usage.
Issue data not yet available.
+1 stars this period — 0.32% growth rate.
Licensed under Apache-2.0. Permissive — safe for commercial use.
Risk scores are computed from real-time repository data. Higher scores indicate healthier metrics.