docs(README): restructure and improve project overview and installation guide#1854
docs(README): restructure and improve project overview and installation guide#1854fishman wants to merge 2 commits into
Conversation
fishman
commented
May 11, 2026
fishman
commented
- Update project tagline to emphasize GPU sharing over virtualization
- Restructure sections, add "problem"/"solution"
- Clarify the architecture flow diagram with labeled stages
- Tighten wording throughout (e.g. "zero application changes" -> "no code changes")
…on guide - Update project tagline to emphasize GPU sharing over virtualization - Restructure sections, add "problem"/"solution" - Clarify the architecture flow diagram with labeled stages - Tighten wording throughout (e.g. "zero application changes" -> "no code changes")
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: fishman The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request significantly updates the README.md to provide a more comprehensive project overview, including a new section on resource contention problems and a refined technical explanation of how HAMi works. The installation and quick-start guides were also expanded with better verification steps. The review feedback identifies an inconsistency in the Discord community links and suggests improving the documentation's usability by replacing generic pod placeholders with the actual names used in the provided examples.
|  | ||
| HAMi (Heterogeneous AI Computing Virtualization Middleware) lets you share GPUs across Kubernetes workloads with memory and compute isolation, without changing application code. Formerly k8s-vGPU-scheduler. | ||
|
|
||
| [Docs](https://docs.project-hami.io) | [Quick Start](#quick-start) | [Discord](https://discord.gg/hami) | [Issues](https://github.com/project-hami/hami/issues) | [Roadmap](ROADMAP.md) | [Contributing](CONTRIBUTING.md) |
There was a problem hiding this comment.
The Discord link https://discord.gg/hami introduced here is inconsistent with the links used in the header (line 14) and the community section (line 201), which both point to https://discord.gg/Amhy7XmbNq. It is recommended to use a single consistent link throughout the document to avoid confusion.
| Verify the workload is running and check GPU allocation: | ||
| ```bash | ||
| kubectl get pods | ||
| kubectl describe pod <pod-name> |
There was a problem hiding this comment.
The example pod defined in examples/nvidia/default_use.yaml is explicitly named gpu-pod. Using this specific name instead of the <pod-name> placeholder makes the quick start guide more user-friendly and directly executable for users following the steps.
| kubectl describe pod <pod-name> | |
| kubectl describe pod gpu-pod |
|
|
||
| Check what the workload sees inside the container: | ||
| ```bash | ||
| kubectl exec <pod-name> -- nvidia-smi |
There was a problem hiding this comment.
Using the explicit pod name gpu-pod from the provided example allows users to copy and paste the command directly without needing to manually substitute a placeholder.
| kubectl exec <pod-name> -- nvidia-smi | |
| kubectl exec gpu-pod -- nvidia-smi |
github-actions
Bot
added
the
kind/documentation
|
Thanks for your pull request. Before we can look at it, you'll need to add a 'DCO signoff' to your commits. 📝 Please follow instructions in the contributing guide to update your commits with the DCO Full details of the Developer Certificate of Origin can be found at developercertificate.org. The list of commits missing DCO signoff:
DetailsInstructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here. |
There was a problem hiding this comment.
3 issues to fix before this can merge.
blocker: dco missing. both commits have no Signed-off-by line. fix with git rebase --signoff HEAD~2 or git commit --amend --signoff on each commit, then force push.
broken link. line with the nav links has [[Contributing](CONTRIBUTING.md) - double bracket. will render as literal text, not a link.
inconsistent discord url. this pr introduces discord.gg/hami but the rest of the file uses discord.gg/Amhy7XmbNq. use one url throughout.
placeholder not replaced. kubectl describe pod <pod-name> and kubectl exec <pod-name> should use gpu-pod, which is the actual name in examples/nvidia/default_use.yaml. users can copy-paste that directly.
2 participants
