predibase/lorax
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs observed · 2026-08-28
Health v2 · maintenance only
62/100
- Activity 84
- Release rhythm 28
- Longevity 74
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: 48
- age_days: 1048
- days_rel: 597
- days_push: 97
- n_releases_24m: 4
Adoption not part of the score
3826 stars · 326 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
LoRAX is a multi-LoRA inference server that serves thousands of fine-tuned LLM adapters on a single GPU by sharing a common base model. It provides an OpenAI-compatible REST API with dynamic adapter loading, heterogeneous continuous batching, and production features like Prometheus metrics and Kubernetes Helm charts.
Use cases
- serve thousands of fine-tuned lora models on one gpu
- host a multi-tenant llm inference server with per-request adapters
- reduce cost of serving many fine-tuned llms
- run an openai-compatible api for custom fine-tuned models
- dynamically load huggingface lora adapters per request
- deploy llm serving on kubernetes with helm
- merge multiple lora adapters into an ensemble at inference time
- serve structured output from fine-tuned llms
When to choose
- you need to serve many fine-tuned LoRA adapters of the same base model cost-effectively
- you want an OpenAI-compatible API with per-request adapter selection
- you need production features like metrics, tracing, and Kubernetes deployment
- you want to merge adapters per request to build ensembles
When to avoid
- you only serve one or a few full fine-tuned models rather than LoRA adapters
- you need non-LoRA fine-tuning methods like full-weight tuning served together
- you need a simple local playground rather than a production serving server
- your base models differ per request, defeating shared-base-model efficiency
Facets
service · maturity active
llm-inference http-server api-framework monitoring tracing large-language-models machine-learning apis self-hosted gpu-computing python self-hosted lora model-serving openai-compatible-api fine-tuned-models adapter-hot-swapping continuous-batching quantization helm-charts docker kubernetes gpu linux
2 sources
- readme: https://github.com/predibase/lorax · fetched 2026-08-28 · 9ce55f7eebce
- homepage: https://loraexchange.ai · fetched 2026-08-29 · 60e544500dc0
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| predibase/lorax | main | 62 |
For agents
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem