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
- Repository: https://github.com/AncientStudying/vllm-grpc
- Changelog: https://github.com/AncientStudying/vllm-grpc/blob/main/CHANGELOG.md
- Issues: https://github.com/AncientStudying/vllm-grpc/issues
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)
| 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)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| 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.