LoRAX
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
LoRAX scores 5/10 (Solid) in Inference & Serving.
Language Python License Apache-2.0 Stars 3.8k★ Type service Self-host Yes Repo predibase/lorax Homepage https://loraexchange.ai
Quality
Solid 5.0
Adoption 40
Activity 28
Maturity 92
Community 39
Capability 50
Show the math
Overall 5/10
value = 5/10
score = value
Adoption 4.6/10
value = 39.5/100
score = 1 + 9 * value / 100
Activity 3.5/10
value = 28.2/100
score = 1 + 9 * value / 100
Maturity 9.3/10
value = 92.4/100
score = 1 + 9 * value / 100
Community 4.5/10
value = 38.8/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
3.8k★ GitHub stars
2/90d Recent commits
1 devs/90d Recent contributors
2.7y Project age
1mo ago Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
- Managed option
Managed option
Available as a hosted/managed service in addition to self-hosting.
lora multi-adapter serving gpu fine-tuning