Source: vLLM docs: Reproducibility
vLLM's statement of what it does and does not guarantee about reproducible outputs: default seed 0, offline multiprocessing switch, batch invariance for online serving.
Contents
- What: official documentation (latest)
- Author: vLLM project
- Date: accessed 2026-11-14
- Original: vLLM docs: Reproducibility
Summary
A short page stating that vLLM trades reproducibility for performance by default, and listing the switches that restore it.
Key claims
- vLLM does not guarantee reproducible results by default.
- Offline: set
VLLM_ENABLE_V1_MULTIPROCESSING=0to make scheduling deterministic, or enable batch invariance so outputs ignore scheduling. - Online serving: only batch invariance is available.
- In the V1 engine the seed defaults to 0 and cannot be unset, so runs match even at temperature > 0; workers need consistent random state for features such as speculative decoding.
- Reproducibility holds only on the same hardware and the same vLLM version.