docs: fix kai-scheduler hamicore install flags (guide + blog + zh)#612
docs: fix kai-scheduler hamicore install flags (guide + blog + zh)#612mesutoezdil wants to merge 2 commits into
Conversation
✅ Deploy Preview for project-hami ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
Warning Review limit reached
Next review available in: 57 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (2)
📝 WalkthroughWalkthroughAdded English and Chinese blog posts and user guides documenting KAI Scheduler’s HAMi-core GPU memory hard isolation integration, including architecture, Helm installation, Pod usage, verification, opt-out controls, rounding behavior, collaboration history, and roadmap. ChangesKAI Scheduler HAMi-core documentation
Estimated code review effort: 2 (Simple) | ~10 minutes Possibly related PRs
Suggested labels: Suggested reviewers: Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
[APPROVALNOTIFIER] This PR is APPROVED Approval requirements bypassed by manually added approval. This pull-request has been approved by: mesutoezdil The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
scheduler.gpuSharing.enabled / scheduler.gpuSharing.hamicoreEnabled don't exist in the kai-scheduler chart (checked v0.16.0 through main); helm ignores unknown --set paths so nothing gets enabled. Use global.gpuSharing and binder.plugins.hamicore.enabled across the guide, blog and zh translations. Signed-off-by: mesutoezdil <mesudozdil@gmail.com>
3155168 to
77f4382
Compare
|
New changes are detected. LGTM label has been removed. |
mesutoezdil
changed the title
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md`:
- Around line 1-4: Rename both blog post directories to use the standard
date-prefixed structure: move
blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md to
blog/2026-06-20-hami-core-adopted-by-nvidia-kai-scheduler/index.md and mirror
the same move for
i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md.
No content changes are required.
- Line 159: Update the locale-specific links for the Chinese content: in
i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md:158,
point the docs link to
/zh/docs/next/userguide/kai-scheduler/how-to-use-kai-scheduler; in
i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md:7,
point the blog link to /zh/blog/hami-core-adopted-by-nvidia-kai-scheduler. The
anchor blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md:159 requires no
direct change.
- Around line 106-110: Pin every KAI Scheduler install snippet to the documented
chart path and release v0.16.4 instead of the floating OCI reference. Update
both snippets in blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md (lines
106-110 and 216-220), both translated blog snippets in
i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md
(lines 105-109 and 215-219), and the install snippets in
docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md (lines 27-31) and its
translated counterpart (lines 27-31), keeping all copies consistent.
In `@docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md`:
- Line 5: Update the KAI Scheduler description to say GPU memory hard isolation
is enabled with two Helm flags, reflecting both global.gpuSharing=true and
binder.plugins.hamicore.enabled=true. Apply the equivalent Chinese wording in
the translated documentation.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: cc23035b-2c40-4fa4-8ddf-947d9ec26cb9
📒 Files selected for processing (4)
blog/hami-core-adopted-by-nvidia-kai-scheduler/index.mddocs/userguide/kai-scheduler/how-to-use-kai-scheduler.mdi18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.mdi18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md
There was a problem hiding this comment.
Caution
Inline review comments failed to post. This is likely due to GitHub's internal server error or limits when posting large numbers of comments. If you are seeing this consistently it is likely a permissions issue. Please check "Moderation" -> "Code review limits" under your organization settings.
Actionable comments posted: 4
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md`:
- Around line 1-4: Rename both blog post directories to use the standard
date-prefixed structure: move
blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md to
blog/2026-06-20-hami-core-adopted-by-nvidia-kai-scheduler/index.md and mirror
the same move for
i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md.
No content changes are required.
- Line 159: Update the locale-specific links for the Chinese content: in
i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md:158,
point the docs link to
/zh/docs/next/userguide/kai-scheduler/how-to-use-kai-scheduler; in
i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md:7,
point the blog link to /zh/blog/hami-core-adopted-by-nvidia-kai-scheduler. The
anchor blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md:159 requires no
direct change.
- Around line 106-110: Pin every KAI Scheduler install snippet to the documented
chart path and release v0.16.4 instead of the floating OCI reference. Update
both snippets in blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md (lines
106-110 and 216-220), both translated blog snippets in
i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md
(lines 105-109 and 215-219), and the install snippets in
docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md (lines 27-31) and its
translated counterpart (lines 27-31), keeping all copies consistent.
In `@docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md`:
- Line 5: Update the KAI Scheduler description to say GPU memory hard isolation
is enabled with two Helm flags, reflecting both global.gpuSharing=true and
binder.plugins.hamicore.enabled=true. Apply the equivalent Chinese wording in
the translated documentation.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: cc23035b-2c40-4fa4-8ddf-947d9ec26cb9
📒 Files selected for processing (4)
blog/hami-core-adopted-by-nvidia-kai-scheduler/index.mddocs/userguide/kai-scheduler/how-to-use-kai-scheduler.mdi18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.mdi18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md
🛑 Comments failed to post (4)
blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md (3)
1-4: 📐 Maintainability & Code Quality | 🟠 Major | ⚡ Quick win
Both blog posts need date-prefixed directories.
blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md#L1-L4: rename underblog/2026-06-20-hami-core-adopted-by-nvidia-kai-scheduler/.i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md#L1-L4: mirror the same date-prefixed directory structure.As per coding guidelines, blog posts must use the standard Docusaurus
YYYY-MM-DD-titledirectory structure.📍 Affects 2 files
blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md#L1-L4(this comment)i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md#L1-L4🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md` around lines 1 - 4, Rename both blog post directories to use the standard date-prefixed structure: move blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md to blog/2026-06-20-hami-core-adopted-by-nvidia-kai-scheduler/index.md and mirror the same move for i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md. No content changes are required.Source: Coding guidelines
106-110: 🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash set -euo pipefail printf '\n## File list\n' git ls-files blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md \ i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md \ docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md \ i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md printf '\n## Relevant excerpts\n' for f in \ blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md \ i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md \ docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md \ i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md do echo echo "### $f" sed -n '1,140p' "$f" | nl -ba | sed -n '1,140p' done printf '\n## Search for kai-scheduler chart references\n' rg -n --hidden --glob '!**/node_modules/**' \ 'ghcr\.io/nvidia/kai-scheduler|kai-scheduler.*oci://|helm install kai-scheduler' . printf '\n## Search for version mentions\n' rg -n --hidden --glob '!**/node_modules/**' 'v0\.16\.4|0\.16\.4|chart version|version-pinned|kai scheduler' .Repository: Project-HAMi/website
Length of output: 598
🌐 Web query:
KAI Scheduler OCI chart ghcr.io/nvidia/kai-scheduler version v0.16.4 documentation💡 Result:
As of July 15, 2026, the KAI Scheduler documentation and Helm chart are hosted primarily via the project's official GitHub repositories [1][2]. The OCI Helm chart for the KAI Scheduler is located at ghcr.io/nvidia/kai-scheduler/kai-scheduler (or the corresponding kai-scheduler/kai-scheduler registry) [3][4][5]. Regarding the specific version v0.16.4: - While some technical documentation references version v0.16.4 [1][2][6][7], the project's release history indicates that recent major feature updates occurred around version v0.16.0 [8][9]. - Documentation and guides for the KAI Scheduler, including installation instructions, configuration details, and quick-start examples, are maintained in the repository's documentation directory and the official GitHub Wiki [3][5][10]. - To install a specific version (such as v0.16.4) using Helm, you can use the following command: helm upgrade -i kai-scheduler oci://ghcr.io/nvidia/kai-scheduler/kai-scheduler -n kai-scheduler --create-namespace --version v0.16.4 [3][4] For the most up-to-date documentation, including release-specific notes and migration guides, please refer to the official KAI Scheduler GitHub releases page and the
docs/folder in the primary repository [5][10]. Users are advised to avoid submitting workloads directly to thekai-schedulerinstallation namespace and instead use a dedicated namespace for their workloads [3][5].Citations:
- 1: https://github.com/kai-scheduler/KAI-Scheduler
- 2: https://github.com/NVIDIA/KAI-Scheduler/releases
- 3: https://github.com/NVIDIA/KAI-Scheduler/blob/f909aece/README.md
- 4: https://kubernetes.recipes/recipes/ai/kai-scheduler-installation/
- 5: https://pkg.go.dev/github.com/NVIDIA/KAI-scheduler@v0.13.0
- 6: https://pkg.go.dev/github.com/kai-scheduler/KAI-scheduler/pkg/scheduler/cache/usagedb/prometheus
- 7: https://pkg.go.dev/github.com/kai-scheduler/KAI-scheduler/test/e2e/suites/allocate/node_order
- 8: https://github.com/NVIDIA/KAI-Scheduler/blob/main/CHANGELOG.md
- 9: https://github.com/kai-scheduler/KAI-Scheduler/releases/tag/v0.16.0
- 10: https://github.com/NVIDIA/KAI-Scheduler?tab=readme-ov-file
🏁 Script executed:
#!/bin/bash set -euo pipefail printf '\n## Current install snippets with context\n' for f in \ blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md \ i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md \ docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md \ i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md do echo echo "### $f" rg -n -C 2 'helm install kai-scheduler|ghcr\.io/nvidia/kai-scheduler|--version|binder\.plugins\.hamicore\.enabled|global\.gpuSharing' "$f" || true done printf '\n## Any pinned Helm installs elsewhere\n' rg -n --hidden --glob '!**/node_modules/**' 'helm install .*--version|oci://.*--version|--version [0-9]' blog docs i18n || trueRepository: Project-HAMi/website
Length of output: 6306
Pin the KAI Scheduler chart everywhere. Replace the floating OCI reference with the documented chart path and add the release version (
v0.16.4) in every install snippet so the blog/docs and translated copies install the same artifact.📍 Affects 4 files
blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md#L106-L110(this comment)blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md#L216-L220i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md#L105-L109i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md#L215-L219docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md#L27-L31i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md#L27-L31🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md` around lines 106 - 110, Pin every KAI Scheduler install snippet to the documented chart path and release v0.16.4 instead of the floating OCI reference. Update both snippets in blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md (lines 106-110 and 216-220), both translated blog snippets in i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md (lines 105-109 and 215-219), and the install snippets in docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md (lines 27-31) and its translated counterpart (lines 27-31), keeping all copies consistent.Source: MCP tools
159-159: 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
set -euo pipefail printf '\n== Repo files of interest ==\n' git ls-files 'blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md' \ 'i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md' \ 'i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md' \ 'docusaurus.config.*' \ 'sidebars.*' \ 'docs/**/*' \ 'i18n/zh/**/*' | sed -n '1,200p' printf '\n== Config outlines ==\n' fd -a 'docusaurus.config.*|sidebars.*' . | sed -n '1,50p' printf '\n== Search for docs/blog routing settings ==\n' rg -n --glob 'docusaurus.config.*' --glob 'src/**/*' --glob 'blog/**/*' --glob 'docs/**/*' --glob 'i18n/**/*' 'baseUrl|url|routeBasePath|blogBasePath|i18n|current|versions|trailingSlash|docsVersion|blog' . printf '\n== Target file excerpts ==\n' for f in \ 'blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md' \ 'i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md' \ 'i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md' do printf '\n--- %s ---\n' "$f" cat -n "$f" | sed -n '1,120p' doneRepository: Project-HAMi/website
Length of output: 50377
🏁 Script executed:
set -euo pipefail printf '\n== docusaurus.config.js relevant slices ==\n' cat -n docusaurus.config.js | sed -n '1,140p' printf '\n--- docs/blog plugin area ---\n' cat -n docusaurus.config.js | sed -n '180,280p' printf '\n--- navbar/locales area ---\n' cat -n docusaurus.config.js | sed -n '300,450p' printf '\n== target file excerpts ==\n' for f in \ 'blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md' \ 'i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md' \ 'i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md' do printf '\n--- %s ---\n' "$f" cat -n "$f" | sed -n '1,80p' done printf '\n== localized blog route conventions ==\n' rg -n '(/zh/blog|/blog|/zh/docs/next|/docs/next|/zh/docs/|/docs/)' src docs i18n/zh/blog i18n/zh/docusaurus-plugin-content-blog i18n/zh/docusaurus-plugin-content-docs/current --glob '!**/*.png' --glob '!**/*.webp' --glob '!**/*.jpg' --glob '!**/*.jpeg' | sed -n '1,200p'Repository: Project-HAMi/website
Length of output: 50378
🏁 Script executed:
set -euo pipefail printf '\n== docusaurus.config.js relevant slices ==\n' cat -n docusaurus.config.js | sed -n '1,140p' printf '\n--- docs/blog plugin area ---\n' cat -n docusaurus.config.js | sed -n '180,280p' printf '\n--- navbar/locales area ---\n' cat -n docusaurus.config.js | sed -n '300,450p' printf '\n== target file excerpts ==\n' for f in \ 'blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md' \ 'i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md' \ 'i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md' do printf '\n--- %s ---\n' "$f" cat -n "$f" | sed -n '1,80p' done printf '\n== localized blog route conventions ==\n' rg -n '(/zh/blog|/blog|/zh/docs/next|/docs/next|/zh/docs/|/docs/)' src docs i18n/zh/docusaurus-plugin-content-blog i18n/zh/docusaurus-plugin-content-docs/current --glob '!**/*.png' --glob '!**/*.webp' --glob '!**/*.jpg' --glob '!**/*.jpeg' | sed -n '1,200p'Repository: Project-HAMi/website
Length of output: 50378
🏁 Script executed:
set -euo pipefail printf '\n== contribute-docs routing guidance ==\n' cat -n docs/contributor/contribute-docs.md | sed -n '180,220p' printf '\n== zh docs/blog route examples around kai-scheduler ==\n' rg -n '/zh/docs/next|/docs/next|/zh/blog|/blog/hami-core-adopted-by-nvidia-kai-scheduler|/docs/userguide/kai-scheduler/how-to-use-kai-scheduler' \ docs i18n/zh --glob '!**/*.png' --glob '!**/*.webp' --glob '!**/*.jpg' --glob '!**/*.jpeg' | sed -n '1,120p'Repository: Project-HAMi/website
Length of output: 9189
Use locale-prefixed routes in the Chinese pages.
i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md: switch the docs link to/zh/docs/next/userguide/kai-scheduler/how-to-use-kai-scheduler.i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md: switch the blog link to/zh/blog/hami-core-adopted-by-nvidia-kai-scheduler.📍 Affects 3 files
blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md#L159-L159(this comment)i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md#L158-L158i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md#L7-L7🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md` at line 159, Update the locale-specific links for the Chinese content: in i18n/zh/docusaurus-plugin-content-blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md:158, point the docs link to /zh/docs/next/userguide/kai-scheduler/how-to-use-kai-scheduler; in i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md:7, point the blog link to /zh/blog/hami-core-adopted-by-nvidia-kai-scheduler. The anchor blog/hami-core-adopted-by-nvidia-kai-scheduler/index.md:159 requires no direct change.docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md (1)
5-5: 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
Correct the Helm flag count.
docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md#L5: say “two Helm flags.”i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md#L5: use the equivalent Chinese wording.The commands require both
global.gpuSharing=trueandbinder.plugins.hamicore.enabled=true.🧰 Tools
🪛 LanguageTool
[grammar] ~5-~5: Use a hyphen to join words.
Context: ...cheduler/KAI-Scheduler) is NVIDIA's open source, Kubernetes-native scheduler for ...(QB_NEW_EN_HYPHEN)
📍 Affects 2 files
docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md#L5-L5(this comment)i18n/zh/docusaurus-plugin-content-docs/current/userguide/kai-scheduler/how-to-use-kai-scheduler.md#L5-L5🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/userguide/kai-scheduler/how-to-use-kai-scheduler.md` at line 5, Update the KAI Scheduler description to say GPU memory hard isolation is enabled with two Helm flags, reflecting both global.gpuSharing=true and binder.plugins.hamicore.enabled=true. Apply the equivalent Chinese wording in the translated documentation.
1 participant
the kai-scheduler install snippets (guide + adoption blog + zh translations) use
--set scheduler.gpuSharing.enabled=true --set scheduler.gpuSharing.hamicoreEnabled=true, but those keys don't exist in the chart (checked v0.16.0 through main), so helm ignores them and nothing gets enabled.fix: use
--set global.gpuSharing=true --set binder.plugins.hamicore.enabled=truein commands and prose. verified withhelm template.companion: kai-scheduler/KAI-Scheduler#1925, Project-HAMi/KAI-resource-isolator#8. reported in kai-scheduler/KAI-Scheduler#1912.