serve logo

serve

archived
pytorch/serve

Serve, optimize and scale PyTorch models in production

GraphCanon updated 2w · GitHub synced 2w

4.3k stars882 forksLast push 1y Java Apache-2.0

Decision brief

Serve offers dedicated support for deploying and scaling PyTorch models with features tailored towards large language model deployment, such as integration with Hugging Face.

Good fit when

  • If you are working primarily with PyTorch-based machine-learning projects that require production-grade deployments.
  • For teams needing to optimize the performance of their models through integration with hardware like GPUs and frameworks like Kubernetes.

Avoid when

  • Avoid if your primary model development is not in PyTorch or requires deployment using a language other than Java.
  • Not suitable if you do not require the fine-grained control and optimization provided by tools such as VLLM or TensorRT-LLM.

Observed Jul 16, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Archived (360d since push)
As of 2w
Provenance
Not a fork · Organization account
As of 2w
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/pytorch/serve

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A toolkit for deploying and scaling PyTorch machine-learning models in production environments with support for LLM deployment and optimization.

Capability facts

Languages
java

Source: github.language · Aug 2, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Aug 2, 2026)

python ./ts_scripts/install_dependencies.py
Source link

Tags

README

🚀 Quick start with TorchServe


---

# Install dependencies
python ./ts_scripts/install_dependencies.py

---

### 🚀 Quick start with TorchServe (conda)

```bash

---

### 🤖 Quick Start LLM Deployment

#### VLLM Engine
```bash

---

# Make sure to install torchserve with pip or conda as described above and login with `huggingface-cli login`
python -m ts.llm_launcher --model_id meta-llama/Llama-3.2-3B-Instruct --disable_token_auth

---

# Make sure to install torchserve with python venv as described above and login with `huggingface-cli login`

---

# pip install -U --use-deprecated=legacy-resolver -r requirements/trt_llm.txt
python -m ts.llm_launcher --model_id meta-llama/Meta-Llama-3.1-8B-Instruct --engine trt_llm --disable_token_auth

---

### 🚢 Quick Start LLM Deployment with Docker

```bash
#export token=<HUGGINGFACE_HUB_TOKEN>
docker build --pull . -f docker/Dockerfile.vllm -t ts/vllm

docker run --rm -ti --shm-size 10g --gpus all -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:8080 -v data:/data ts/vllm --model_id meta-llama/Meta-Llama-3-8B-Instruct --disable_token_auth

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.