-
Notifications
You must be signed in to change notification settings - Fork 804
[Doc] Fix user guide error for v0.11.0-dev #5107
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
Signed-off-by: MengqingCao <[email protected]>
Signed-off-by: wangxiyuan <[email protected]>
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.
Code Review
This pull request updates documentation to align with the v0.11.0 release, including version numbers, feature statuses, and links. My review identified a couple of incorrect links in the feature support matrix which could negatively impact users. The feedback provided aims to correct these documentation errors.
| | Guided Decoding | 🟢 Functional | See detailed note: [Structured Output Guide][guided_decoding] | | ||
| | Tensor Parallel | 🟢 Functional | Make TP >4 work with graph mode. | | ||
| | Pipeline Parallel | 🟡 Planned | Broken in this version, will fix in next release. | | ||
| | Expert Parallel | 🟢 Functional | See detailed note: [Expert Load Balance (EPLB)][graph_mode] | |
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.
The link for "Expert Parallel" points to the "Graph Mode Guide", which does not seem to contain information about Expert Load Balance (EPLB). The relevant configuration details for EPLB are in the "Additional Configuration" guide. Please update the link to point to the correct document.
For example, you could change the reference to [eplb] and add a new link definition for it at the end of the file:
[eplb]: https://docs.vllm.ai/projects/ascend/en/v0.11.0-dev/user_guide/configuration/additional_config.html
| | Expert Parallel | 🟢 Functional | See detailed note: [Expert Load Balance (EPLB)][graph_mode] | | |
| | Expert Parallel | 🟢 Functional | See detailed note: [Expert Load Balance (EPLB)][eplb] | |
| | Quantization | 🟢 Functional | W8A8 available; working on more quantization method support (W4A8, etc) | | ||
| | Graph Mode | 🔵 Experimental| Experimental, see detailed note: [vllm-ascend#767][graph_mode] | | ||
| | Sleep Mode | 🟢 Functional | | | ||
| | Quantization | 🟢 Functional | See detailed note: [Quantization Guide][qaunt] | |
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.
There's a typo in the link reference for the "Quantization Guide". It's written as [qaunt], but the link is defined as [quant]. This results in a broken link.
| | Quantization | 🟢 Functional | See detailed note: [Quantization Guide][qaunt] | | |
| | Quantization | 🟢 Functional | See detailed note: [Quantization Guide][quant] | |
Pick from #5098 to fix the doc error