ModelEngine-Group / ModelEngine-Group/unified-cache-management
[Bug]: ucm0.5.0rc1对于双节点的共享存储报错
Open
Nobody has claimed this yet.
bug
- Dominant language
- C++
- Stars
- 334
- Forks
- 119
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 82
Description
Your current environment
Glm4.7 vllm-ascend 0.17.0rc1 ucm 0.5.0rc1 910b4双节点 单节点8×64
🐛 Describe the bug
用ucm的example两种模式都试过了，还是报错，现在两个节点用的是共享存储。详细参数请见上个usage
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 by reproducing the failure with the UCM examples in both modes on the reported two-node, shared-storage setup, using the versions and hardware listed in the environment section. Review the usage parameters referenced by the report and the attached error output; done means identifying and fixing the shared-storage failure so both example modes run successfully.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- ai-infra-agents, distributed-systems
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100