Metadata-Version: 2.5
Name: swo-bench
Version: 3.5.0
Summary: Measure inference endpoint performance with real agentic coding workloads
Project-URL: Homepage, https://swarmone.ai/docs/swo-bench
Project-URL: Documentation, https://swarmone.ai/docs/swo-bench
Author-email: SwarmOne <eng@swarmone.ai>
License: Proprietary
Keywords: agentic,benchmark,gpu,inference,llm,sglang,vllm
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: System :: Benchmark
Requires-Python: >=3.10
Requires-Dist: click>=8.0
Requires-Dist: cryptography>=42.0
Requires-Dist: fastapi>=0.110
Requires-Dist: httpx>=0.25
Requires-Dist: msgpack>=1.0
Requires-Dist: orjson>=3.9
Requires-Dist: rich>=13.0
Requires-Dist: uvicorn>=0.27
Requires-Dist: zstandard>=0.22
Provides-Extra: deepseek
Provides-Extra: dev
Requires-Dist: pydantic>=2.13; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
Requires-Dist: pytest>=7.0; extra == 'dev'
Requires-Dist: respx>=0.20; extra == 'dev'
Requires-Dist: ruff>=0.4; extra == 'dev'
Requires-Dist: transformers>=4.40; extra == 'dev'
Provides-Extra: dynosim
Requires-Dist: transformers>=4.40; extra == 'dynosim'
Provides-Extra: http2
Requires-Dist: h2>=4.1; extra == 'http2'
Description-Content-Type: text/markdown

# swo-bench

`swo-bench` measures inference-endpoint performance with recorded and catalog
agentic workloads. Start with:

```console
swo-bench replay --help
```

Product documentation, examples, and support information are available at
https://swarmone.ai/docs/swo-bench.
