Skip to main content

SMG Python Bindings

This directory contains the Python bindings for SMG (Shepherd Model Gateway), built using maturin and PyO3.

Quick Start

Installation

pip install maturin
cd smg/bindings/python
maturin develop --features vendored-openssl

Usage

The smg serve command launches backend workers and the SMG router in a single command:

# sglang with gRPC (default)
smg serve --backend sglang --model-path /path/to/model --port 8080

# sglang with HTTP
smg serve --backend sglang --model-path /path/to/model --port 8080 --connection-mode http

# vLLM (gRPC only)
smg serve --backend vllm --model /path/to/model --port 8080

# TensorRT-LLM (gRPC only)
smg serve --backend trtllm --model /path/to/model --port 8080

# Multiple workers (data parallel)
smg serve --backend sglang --model-path /path/to/model --port 8080 --dp-size 4

Serve Options

Option Default Description
--backend sglang Backend to use: sglang, vllm, or trtllm
--connection-mode grpc Connection mode: grpc or http. vllm/trtllm only support grpc
--host 127.0.0.1 Host for the router
--port 8080 Port for the router
--dp-size 1 Data parallel size (number of worker replicas)
--worker-host 127.0.0.1 Host for worker processes
--worker-base-port 31000 Base port for workers
--worker-startup-timeout 300 Seconds to wait for workers to become healthy

Backend-specific options (e.g., --tensor-parallel-size, --quantization) are passed through to the backend.

Directory Structure

bindings/python/
├── src/                    # Source code (src layout)
│   ├── lib.rs              # Rust/PyO3 bindings implementation
│   └── smg/                # Python source code
│       ├── __init__.py
│       ├── cli.py          # CLI entry point
│       ├── serve.py        # smg serve implementation
│       ├── launch_router.py
│       ├── router.py
│       └── router_args.py
├── tests/                  # Python unit tests
├── Cargo.toml              # Rust package configuration
├── pyproject.toml          # Python package configuration
└── README.md               # This file

Building

Development Build

pip install maturin
cd smg/bindings/python
maturin develop --features vendored-openssl

Production Build

cd smg/bindings/python
maturin build --release --out dist --features vendored-openssl
pip install dist/smg-*.whl

Testing

cd smg/bindings/python
pytest tests/

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tokenspeed_smg-1.10.1.post20260828.tar.gz (3.6 MB view details)

Uploaded Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

tokenspeed_smg-1.10.1.post20260828-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (33.0 MB view details)

Uploaded CPython 3.8+manylinux: glibc 2.17+ x86-64

tokenspeed_smg-1.10.1.post20260828-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (34.7 MB view details)

Uploaded CPython 3.8+manylinux: glibc 2.17+ ARM64

File details

Details for the file tokenspeed_smg-1.10.1.post20260828.tar.gz.

File metadata

File hashes

Hashes for tokenspeed_smg-1.10.1.post20260828.tar.gz
Algorithm Hash digest
SHA256 6e45df07bb392c78a4cecc0069447f03af8912e22a7a90f23b73801c8206d4bd
MD5 9dac938ea7a96496cc6392058680fc03
BLAKE2b-256 a34108f928466682d252d36e309a0d4eb4328c16fc84632b2af4a8877cd62a5d

See more details on using hashes here.

Provenance

The following attestation bundles were made for tokenspeed_smg-1.10.1.post20260828.tar.gz:

Publisher: tokenspeed-smg.yml on lightseekorg/tokenspeed-third-party

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file tokenspeed_smg-1.10.1.post20260828-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for tokenspeed_smg-1.10.1.post20260828-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 d53e1b8a3e79485312674f182c6b7a658779bff25a5f8c86976a4c6af4b1951e
MD5 974cfa95393d9811057ffb229a120bdf
BLAKE2b-256 52a322d95072938ab88ec5dd17d01c65884c7316128d995f5db4da5175cc8087

See more details on using hashes here.

Provenance

The following attestation bundles were made for tokenspeed_smg-1.10.1.post20260828-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: tokenspeed-smg.yml on lightseekorg/tokenspeed-third-party

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file tokenspeed_smg-1.10.1.post20260828-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for tokenspeed_smg-1.10.1.post20260828-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 003d596480e3787b7d940ecf1189f27960ab5243aacc0743bdd6afce4c41a5af
MD5 36a6642532d6475c12174434d812fa0f
BLAKE2b-256 5e4340266541fb60908b80d4d9debc3509ac5c7703397e943a84b6d81ef41f24

See more details on using hashes here.

Provenance

The following attestation bundles were made for tokenspeed_smg-1.10.1.post20260828-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl:

Publisher: tokenspeed-smg.yml on lightseekorg/tokenspeed-third-party

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

1.10.1.post20260828 This release

3 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page