device bug
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
https://github.com/lm-sys/FastChat/blob/main/fastchat/model/compression.py#L49
hello, i found that this line of code does not set the tensor in the weight of the tuple type to the corresponding device, causing problems with multi-card inference.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at fastchat/model/compression.py:49 and reproduce the reported multi-card inference failure, tracing how the tuple-typed weight is handled. Done means the tensor in that weight is placed on the corresponding device and multi-card inference no longer shows the reported problem; add or run a regression test if the repository provides one.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100