vllm-grpc-frontend
The gRPC frontend server for vllm-grpc.
It wraps vLLM's V1 AsyncLLM engine and serves the project's protobuf
ChatService, CompletionsService, and HealthService over gRPC.
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 frontend works with.
Install
pip install vllm-grpc-frontend
The base install pulls no vLLM, so it succeeds on any platform — including those without a vLLM wheel. vLLM is required only to actually run the engine.
vLLM prerequisite (V1 engine)
The frontend drives vLLM's V1 AsyncLLM API, so it requires vllm>=0.20.
Install it via the opt-in engine extra:
pip install "vllm-grpc-frontend[engine]" # pulls vllm>=0.20
Or provide vLLM yourself — useful on platforms where the stock wheel does not
build (for example macOS, which uses vllm-metal). If vLLM is missing at
runtime, the server raises an ImportError when it starts; the package still
installs fine without it.
Run
The package installs a vllm-grpc-frontend console script:
vllm-grpc-frontend # serves gRPC on 0.0.0.0:50051 by default
Configure with environment variables:
MODEL_NAME— model to load (defaultQwen/Qwen3-0.6B)FRONTEND_HOST/FRONTEND_PORT— bind address (default0.0.0.0:50051)
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-frontend 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_frontend-0.1.0.tar.gz | 16.9 kB | Without provenance | Details for vllm_grpc_frontend-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| vllm_grpc_frontend-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for vllm_grpc_frontend-0.1.0-py3-none-any.whl |
Total release size: 30.1 kB
Release files / vllm_grpc_frontend-0.1.0.tar.gz
| Download URL | vllm_grpc_frontend-0.1.0.tar.gz |
|---|---|
| Size | 16.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3f2c86c58f68f51fc277fffa12d1eb49ecd6fd482d3b04f29dfadf3ad2eed7c1
|
|
BLAKE2b-256 checksum How to use checksums |
246932a936d3178b15fabfaf2642bb3a5fa17acf28f772ca39381a379bc70b3d
|
| 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_frontend-0.1.0-py3-none-any.whl
| Download URL | vllm_grpc_frontend-0.1.0-py3-none-any.whl |
|---|---|
| Size | 13.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ce3afc41f91c803fbce2863f445ce1ea380f010210ea318cbd90cb4e22cfc39e
|
|
BLAKE2b-256 checksum How to use checksums |
980353d7ff802d3df3cb0e44daed6b3f5f2159258e23e52de43e4bf048ee2dac
|
| 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-frontend 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.