# tensorflow/serving

A flexible, high-performance serving system for machine learning models

Repository: https://github.com/tensorflow/serving
Canonical: https://ross.abutalabs.com/products/serving
Homepage: https://www.tensorflow.org/serving
Language: C++
License: Apache-2.0
License Family: permissive
Topics: machine-learning, deep-learning, deep-neural-networks, python, cpp, neural-network, ml, serving, tensorflow
Last push: 2026-08-26T22:24:40+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 62, longevity 100
- inputs: {"age_days": 3872, "days_push": 7, "days_rel": 92, "gap_med": 106, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6360, forks 2206 (observed 2026-08-28T04:09:42.811373+00:00)

## What it is
TensorFlow Serving is a flexible, high-performance serving system for machine learning models designed for production environments. It manages model lifetimes after training, exposing gRPC and REST inference endpoints with versioned access, batching, and canary/A/B deployment support.

## Use cases
- serve tensorflow models in production
- deploy trained ml models behind a rest or grpc api
- run model inference with gpu batching
- roll out new model versions without changing client code
- a/b test or canary experimental models
- serve multiple model versions simultaneously
- host saved_model exports in docker

## When to choose
- you need production-grade, low-latency serving of TensorFlow SavedModel files
- you want versioned model deployment, canarying, and A/B testing out of the box
- you need both gRPC and REST inference endpoints with request batching on GPU
- you want a battle-tested, Docker-deployable inference server maintained by Google

## When to avoid
- your models are PyTorch, ONNX, or other non-TensorFlow formats - consider TorchServe, Triton, or ONNX Runtime instead
- you need lightweight edge or mobile inference - use TensorFlow Lite instead
- you only need simple experimental inference in a notebook - loading the model directly in Python is simpler
- you need LLM-specific features like token streaming or KV-cache management - dedicated LLM servers fit better

## Facets
- artifact type: service
- maturity: stable
- function: llm-inference, machine-learning, rpc, http-server, gpu-computing
- domain: machine-learning, deep-learning, large-language-models, apis
- platform: self-hosted, cpp, python
- tags: model-serving, inference-server, tensorflow, grpc, rest-api, model-versioning, production-ml, batching, devops, docker, linux, gpu

## Member repositories
- tensorflow/serving (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:42.811373+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 2026-08-29T17:46:05.333400+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/serving (fetched 2026-08-28T04:09:42.811373+00:00, sha 045585282949)
  - homepage: https://www.tensorflow.org/serving (fetched 2026-08-29T08:42:24.773245+00:00, sha badf76ae3775)
  - site_page: https://www.tensorflow.org/install (fetched 2026-08-29T08:42:24.828319+00:00, sha 584a762da891)
  - site_page: https://www.tensorflow.org/tfx/api_docs (fetched 2026-08-29T08:42:24.912150+00:00, sha 6977825696fe)
  - site_page: https://www.tensorflow.org/about (fetched 2026-08-29T08:42:24.962304+00:00, sha 817250744d91)
  - site_page: https://www.tensorflow.org/about/case-studies (fetched 2026-08-29T08:42:24.992201+00:00, sha e6701029eec0)
  - site_page: https://www.tensorflow.org/tfx/data_validation/install (fetched 2026-08-29T08:42:25.035560+00:00, sha 44786da3992b)
  - site_page: https://www.tensorflow.org/tfx/transform/install (fetched 2026-08-29T08:42:25.100394+00:00, sha 95876a677235)
  - site_page: https://www.tensorflow.org/community/contribute (fetched 2026-08-29T08:42:24.933689+00:00, sha 77d394fa76e7)
- Data as of 2026-08-30T08:39:29.467469+00:00.