[BUG] RWKV Models are not configured to use Cuda GPU lists.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
The file (fastchat/model/rwkv_model.py) has a RWKV stratergy (strategy="cuda fp16") being set that is not imlemented to use the native --gpus or --num-gpus fschat command arguments.
Example, Launching a model worker with (--num-gpus 4 --gpus 0,1,2,3) does not spawn the RWKV instance with these GPU specifications and just uses GPU 1
strategy="cuda fp16"
VS.
strategy="cuda:0 fp16 -> cuda:1 fp16 -> cuda:2 fp16 -> cuda:3 fp16 -> cuda:4 fp16"
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 in fastchat/model/rwkv_model.py and trace how the RWKV strategy is created for a model worker. Compare that setup with handling of --gpus and --num-gpus; done means the RWKV instance honors the requested GPU list and count rather than defaulting to GPU 1.
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
- 35/100