How to use multiple Ascend NPUs?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
Why is the --device npu parameter fixed to support only one Ascend NPU in code instead of multiple NPUs?
` def generate_stream_gate(self, params):`
` if self.device == "npu":`
` import torch_npu`
` torch_npu.npu.set_device("npu:0")`
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 the implementation containing generate_stream_gate and trace how --device npu is selected and passed to Ascend. Determine the intended multi-NPU behavior and configuration from the surrounding serving code; done means the npu path no longer forces npu:0 and multi-NPU use is verified on Ascend hardware.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100