# S-LoRA/S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Repository: https://github.com/S-LoRA/S-LoRA
Canonical: https://ross.abutalabs.com/products/s-lora
Homepage: https://arxiv.org/abs/2311.03285
Language: Python
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2024-01-21T10:41:56+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 73
- inputs: {"age_days": 1032, "days_push": 955, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1923, forks 126 (observed 2026-08-28T04:05:55.295050+00:00)

## What it is
S-LoRA is a serving system for large language models that scales to thousands of concurrent LoRA adapters on one or more GPUs. It uses Unified Paging to manage adapter weights and KV cache in a unified memory pool, plus custom CUDA kernels and tensor parallelism for heterogeneous batching.

## Use cases
- serve thousands of LoRA adapters from one base model
- host many task-specific fine-tuned LLMs on a single GPU
- improve LLM serving throughput with batched LoRA inference
- run multi-adapter inference across multiple GPUs
- deploy a fine-tuning-as-a-service backend
- benchmark LoRA serving performance against vLLM and PEFT

## When to choose
- you need to serve many LoRA adapters derived from a single base model
- adapter count or memory fragmentation limits your current vLLM/PEFT setup
- you want research-grade multi-adapter serving with tensor parallelism

## When to avoid
- you serve a single model without adapters - use vLLM or similar instead
- you need recent model support or active maintenance - the project is in maintenance mode
- you lack an Ampere-class CUDA GPU with bfloat16 support
- you need a production-supported inference stack with broad ecosystem compatibility

## Facets
- artifact type: service
- maturity: maintenance
- function: llm-inference, machine-learning, gpu-computing
- domain: large-language-models, machine-learning, deep-learning
- platform: python
- tags: lora, model-serving, inference-server, cuda-kernels, tensor-parallelism, batched-inference, linux, gpu, docker

## Member repositories
- S-LoRA/S-LoRA (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:55.295050+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:09:37.602929+00:00, confidence not recorded.
  - readme: https://github.com/S-LoRA/S-LoRA (fetched 2026-08-28T04:05:55.295050+00:00, sha 6c84a5d72f14)
  - homepage: https://arxiv.org/abs/2311.03285 (fetched 2026-08-29T10:49:01.129404+00:00, sha 1362aaa4845d)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T10:49:01.138559+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T10:49:01.144101+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T10:49:01.146545+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T10:49:01.141341+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.