vllm-project/vllm v0.25.1
Avoid blocking model launching when no system FFmpeg is available for TorchCodec (#47888).
Key points
- This release features 2 commits from 2 contributors (1 new)!
- v0.25.1 is a patch release containing two targeted bug fixes on top of v0.25.0.
- Previously import torchcodec raised a RuntimeError at import time when system FFmpeg was missing, which blocked startup (e.g. vllm serve Qwen/Qwen3-VL-2B-Instruct) even when TorchCodec was not in use.
- Guard mixed-dtype allreduce RMSNorm quant fusions (#48330).
Sources (1)
- [1]vllm-project/vllm v0.25.1GitHub: vllm-project/vllm · Jul 14, 08:51 AM
* **Avoid blocking model launching when no system FFmpeg is available for TorchCodec** (#47888).
This release features 2 commits from 2 contributors (1 new)!
Extractive summary: sentences quoted from the sources.