bytedance / bytedance/MegaTTS3
CUDA out of memory. Tried to allocate 24.00 MiB. GPU
Open
- Dominant language
- Python
- Stars
- 6.1k
- Forks
- 474
- PR merge metrics
- No merged PRs in 30d
Description
支持多卡GPU推理吗？
我有4块T4 16G,显卡，现在提示要24G，能不能多卡推理？？
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue does not name an inference file, test, or entry point. Start by locating the inference entry point and reviewing how devices and model memory are selected; define done as a documented, tested answer on whether the four available GPUs can be used for inference without the reported allocation failure.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100