jd-opensource / jd-opensource/JoyAI-VL-Interaction
rtsp首次推理比较慢，建议添加VLLM预热、解码器预热功能
Open
- Dominant language
- Python
- Stars
- 1.9k
- Forks
- 190
- PR merge metrics
- No merged PRs in 30d
Description
This issue has no description.
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue mentions slow first inference for RTSP, plus VLLM and decoder warmup, but names no files, tests, or entry points. Start by locating the RTSP inference path and the VLLM and decoder initialization points. Done means the first inference no longer incurs the reported startup delay, with a regression check if the repository provides one.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- performance
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100