deepseek-ai / deepseek-ai/profile-data
Is the prefill.json generated through code similar to dualpipe?
Open
- Dominant language
- No language data
- Stars
- 1.2k
- Forks
- 152
- PR merge metrics
- No merged PRs in 30d
Description
From the DualPipe code, it appears to be pipeline parallelism. However, in the introduction article about the inference system on Saturday, it was mentioned that the parallelism strategy does not include pipeline parallelism.
thanks.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.