-
Notifications
You must be signed in to change notification settings - Fork 110
[Docs] preparation for version 3.0 #760
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
CONTRIBUTING.md
Outdated
In pull requests, contributor should describe what changed and why. Please also provide test cases if applicable. | ||
Pull requests require approvals from __one members__ before merging. Additionally, they must pass continuous integration checks. More details see [Code Contribution](docs/code_countribution.md) | ||
Pull requests require approvals from **one members** before merging. Additionally, they must pass continuous integration checks. More details see [Code Contribution](docs/code_countribution.md) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why is one member
in plural form?
- support reduction operators: cumsum, layernorm, mean, softmax | ||
- support 183 operators in total, including custom operators used in large model inference | ||
- support more hardware platforms, add Ascend, AIPU, etc. | ||
- compatible with the vLLM framework, with the inference verification of DeepSeek model passed |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
V3 or R1? To be specific.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
V3 and R1 share the same structure, and we have verified DeepSeek R1.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
PR Category
OP Test & Docs
Type of Change
Documentation Update
Description
Issue
Progress
Performance