Skip to main content

vllm-grpc-client

A lean async gRPC client for the vllm-grpc frontend. It speaks the project's protobuf ChatService and CompletionsService directly over gRPC — no web-server stack, no fastapi/uvicorn pulled in. The generated stubs (vllm-grpc-gen) install transitively.

Affiliation: vllm-grpc is an independent, community project and is not affiliated with, endorsed by, or sponsored by the vLLM project. "vLLM" is used here only to identify the inference engine this project works with.

Install

pip install vllm-grpc-client

Usage

import asyncio

from vllm_grpc_client import VllmGrpcClient


async def main() -> None:
    async with VllmGrpcClient("localhost:50051") as client:
        result = await client.chat.complete(
            messages=[{"role": "user", "content": "Hello!"}],
            model="Qwen/Qwen3-0.6B",
            max_tokens=64,
        )
        print(result.content)


asyncio.run(main())

client.completions.complete(...) and the streaming variants (client.chat.complete_stream(...), client.completions.complete_stream(...)) follow the same shape.

Links

License

MIT

Metadata

Release files for vllm-grpc-client 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for vllm-grpc-client 0.1.0
File Size Uploaded Provenance Actions
vllm_grpc_client-0.1.0.tar.gz 6.8 kB Without provenance Details for vllm_grpc_client-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for vllm-grpc-client 0.1.0
File Interpreter ABI Platform Actions
vllm_grpc_client-0.1.0-py3-none-any.whl Python 3 none any Details for vllm_grpc_client-0.1.0-py3-none-any.whl

Total release size: 12.0 kB

Release files / vllm_grpc_client-0.1.0.tar.gz

Download URL vllm_grpc_client-0.1.0.tar.gz
Size 6.8 kB
Tags Source
SHA-256 checksum
How to use checksums
b8c7d3d6109cf659ca5560438594497a9dfa81d7bdbb32b0ffda5f342f06f13a
BLAKE2b-256 checksum
How to use checksums
53e3771889868b307496886950f2bc1fa39d4dd6c81dae0a071e0d1a7871d3e9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.12

Release files / vllm_grpc_client-0.1.0-py3-none-any.whl

Download URL vllm_grpc_client-0.1.0-py3-none-any.whl
Size 5.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d373fc5c7c5e480b4aea38cb85d5d401c867fa0efd47daa506ca0625c511436b
BLAKE2b-256 checksum
How to use checksums
a6699752b451aa677c3f94e730bc8a6879542129b79525d0facca3e3bc077285
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.12

Security for vllm-grpc-client 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

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