Metadata-Version: 2.5
Name: servecast
Version: 0.0.1
Summary: Predicts LLM serving performance (TTFT, TPOT, throughput) on a GPU running vLLM. This release only reserves the name.
Project-URL: Homepage, https://github.com/servecast/servecast
Author: The ServeCast authors
License-Expression: Apache-2.0
License-File: LICENSE
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.11
Description-Content-Type: text/markdown

# ServeCast

ServeCast predicts the serving performance of a large language model (time to first token, time per output token,
throughput) on a GPU running vLLM, from a calibrated cost law and a workload.

This repository is being prepared. The first release, its documentation and its source will appear here.

Licensed under the Apache License, Version 2.0 (see `LICENSE`).
