geonminkim99/ServePlay-oss

Measure whether your LLM serving engine actually applied the scheduling policy — or just accepted the config.

0 stars 0 forks 0 watchers Python Apache License 2.0

benchmarking continuous-batching gpu llm llm-serving mlops python scheduler sglang vllm

1 Open Issue Need Help Last updated: Aug 26, 2026

Open Issues Need Help

enhancement help wanted

Measure whether your LLM serving engine actually applied the scheduling policy — or just accepted the config.

Python

#benchmarking#continuous-batching#gpu#llm#llm-serving#mlops#python#scheduler#sglang#vllm