René's URL Explorer Experiment


Title: cuda.core: fix the peer-access cleanup before pool destroy by Andy-Jost · Pull Request #2871 · NVIDIA/cuda-python · GitHub

Open Graph Title: cuda.core: fix the peer-access cleanup before pool destroy by Andy-Jost · Pull Request #2871 · NVIDIA/cuda-python

X Title: cuda.core: fix the peer-access cleanup before pool destroy by Andy-Jost · Pull Request #2871 · NVIDIA/cuda-python

Description: CUDA Python: Performance meets Productivity. Contribute to NVIDIA/cuda-python development by creating an account on GitHub.

Open Graph Description: Summary Closes #2807. clear_mempool_peer_access(), the nvbug 5698116 workaround that runs before cuMemPoolDestroy, has never taken effect. It put every device, including the pool's own, into on...

X Description: Summary Closes #2807. clear_mempool_peer_access(), the nvbug 5698116 workaround that runs before cuMemPoolDestroy, has never taken effect. It put every device, including the pool's own, int...

Opengraph URL: https://github.com/NVIDIA/cuda-python/pull/2871

X: @github

direct link

Domain: github.com

react-profiling0
react-import-mapreact,react-dom,react-dom/client,react-dom/profiling,react-is,react-reconciler,react/compiler-runtime,react/jsx-dev-runtime,react/jsx-runtime,scheduler@d5750093facf
route-pattern/_view_fragments/voltron/pull_requests/show/:user_id/:repository/:id/pull_request_layout(.:format)
route-controllervoltron_pull_requests_fragments
route-actionpull_request_layout
fetch-noncev2:67defcab-0a2a-984d-6aca-f0ee1f0f7a3e
current-catalog-service-hashae870bc5e265a340912cde392f23dad3671a0a881730ffdadd82f2f57d81641b
request-id911C:2068A3:3D9E65:5488CC:6AF83BDC
html-safe-nonce15cae4866372357194da76c44812b693417fd8a09174521e26450da668165bdd
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiI5MTFDOjIwNjhBMzozRDlFNjU6NTQ4OENDOjZBRjgzQkRDIiwidmlzaXRvcl9pZCI6IjgxMjU5MjE2NTU4NzMwOTI1NzMiLCJyZWdpb25fZWRnZSI6ImlhZCIsInJlZ2lvbl9yZW5kZXIiOiJpYWQifQ==
visitor-hmac39fad7e33cd6aac786eba08a0946d657dd4f24aa1cab7ca9aaad0bdec7597e51
hovercard-subject-tagpull_request:4542053945
github-keyboard-shortcutsrepository,pull-request-list,pull-request-conversation,pull-request-files-changed,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location///voltron/pull_requests_fragments/pull_request_layout
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/_view_fragments/voltron/pull_requests/show/NVIDIA/cuda-python/2871/pull_request_layout
twitter:imagehttps://opengraph.githubassets.com/ec0ff40b65677eb52ff8704ad868f36bd007e227bec3d65d69b314ce864f0835/NVIDIA/cuda-python/pull/2871
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/ec0ff40b65677eb52ff8704ad868f36bd007e227bec3d65d69b314ce864f0835/NVIDIA/cuda-python/pull/2871
og:image:altSummary Closes #2807. clear_mempool_peer_access(), the nvbug 5698116 workaround that runs before cuMemPoolDestroy, has never taken effect. It put every device, including the pool's own, into on...
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
og:author:usernameAndy-Jost
hostnamegithub.com
expected-hostnamegithub.com
None5713ecd83001b2f55c3509fb7a292bf7d66d0f167c7ae87a9f7eaec5a52bf8db
turbo-cache-controlno-cache
go-importgithub.com/NVIDIA/cuda-python git https://github.com/NVIDIA/cuda-python.git
octolytics-dimension-user_id1728152
octolytics-dimension-user_loginNVIDIA
octolytics-dimension-repository_id381173759
octolytics-dimension-repository_nwoNVIDIA/cuda-python
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forkfalse
octolytics-dimension-repository_network_root_id381173759
octolytics-dimension-repository_network_root_nwoNVIDIA/cuda-python
turbo-body-classeslogged-out env-production page-responsive
disable-turbofalse
browser-stats-urlhttps://api.github.com/_private/browser/stats
browser-errors-urlhttps://api.github.com/_private/browser/errors
release653be32ff5c755082a4db662491bfbbcfc9112c1
ui-targetfull
theme-color#1e2327
color-schemelight dark
react-app-namepull-requests

Links:

Skip to contenthttps://github.com/NVIDIA/cuda-python/pull/2871#start-of-content
https://github.com/
Sign inhttps://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FNVIDIA%2Fcuda-python%2Fpull%2F2871
GitHubRepository hosting, code review, and collaborationhttps://github.com/platform
CopilotAI coding agent for tasks, projects, and automated workhttps://github.com/features/copilot
ActionsCI/CD and automationhttps://github.com/features/actions
Code QualityQuality analysis, fixes, and enforcementhttps://github.com/features/code-quality
CodespacesCloud development environmentshttps://github.com/features/codespaces
Code SecurityVulnerability detection and remediationhttps://github.com/security/advanced-security/code-security
Secret ProtectionSecret scanning and leak preventionhttps://github.com/security/advanced-security/secret-protection
All Featureshttps://github.com/features
Documentationhttps://docs.github.com/en
Traininghttps://learn.github.com/skills
Certificationshttps://learn.github.com/credentials
Build with Copilothttps://github.com/features/ai
Customize Copilothttps://docs.github.com/en/copilot/how-tos/copilot-on-github/customize-copilot/customize-copilot-overview
Integrationshttps://github.com/marketplace
Trending reposhttps://github.com/trending
GitHub Sponsorshttps://github.com/open-source/sponsors
Developer articleshttps://github.com/resources/articles
ChangelogYour source for the latest features, improvements, and fixes across GitHub products, all in one place.https://github.blog/changelog/
Enterpriseshttps://github.com/enterprise
Teamhttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
Healthcarehttps://github.com/solutions/industry/healthcare
Financial serviceshttps://github.com/solutions/industry/financial-services
Manufacturinghttps://github.com/solutions/industry/manufacturing
Governmenthttps://github.com/solutions/industry/government
See all industrieshttps://github.com/solutions/industry
Why GitHubhttps://github.com/why-github
Customer Storieshttps://github.com/customer-stories
Business insightshttps://github.com/solutions/executive-insights
Trust Centerhttps://github.com/trust-center
GitHub Advanced SecurityEnterprise-grade code securityhttps://github.com/security/advanced-security
Copilot for businessEnterprise-grade AI featureshttps://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 supporthttps://github.com/enterprise/premium-support
Documentationhttps://docs.github.com/en
Resource centerhttps://github.com/resources
Bloghttps://github.blog/
Events & webinarshttps://github.com/resources/events
Community Forumhttps://github.com/orgs/community/discussions
Customer Storieshttps://github.com/customer-stories
Integrationshttps://github.com/marketplace
Customer supporthttps://help.github.com/
Traininghttps://learn.github.com/skills
GitHub Statushttps://www.githubstatus.com/
Abouthttps://github.com/about
Partnershttps://github.com/partners
Changeloghttps://github.blog/changelog/
GitHub UniverseThe event for developers, by developers — talks, workshops, and what’s next for GitHub.https://githubuniverse.com/
Pricinghttps://github.com/pricing
Sign inhttps://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FNVIDIA%2Fcuda-python%2Fpull%2F2871
Sign uphttps://github.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E%2Fvoltron%2Fpull_requests_fragments%2Fpull_request_layout&source=header-repo&source_repo=NVIDIA%2Fcuda-python
Reloadhttps://github.com/NVIDIA/cuda-python/pull/2871
Reloadhttps://github.com/NVIDIA/cuda-python/pull/2871
Reloadhttps://github.com/NVIDIA/cuda-python/pull/2871
NVIDIAhttps://github.com/NVIDIA
cuda-pythonhttps://github.com/NVIDIA/cuda-python
Codehttps://github.com/NVIDIA/cuda-python
Issues219 (219)https://github.com/NVIDIA/cuda-python/issues
Pull requests92 (92)https://github.com/NVIDIA/cuda-python/pulls
Discussionshttps://github.com/NVIDIA/cuda-python/discussions
Actionshttps://github.com/NVIDIA/cuda-python/actions
Projectshttps://github.com/NVIDIA/cuda-python/projects
Wikihttps://github.com/NVIDIA/cuda-python/wiki
Security and qualityhttps://github.com/NVIDIA/cuda-python/security
Insightshttps://github.com/NVIDIA/cuda-python/pulse
https://github.com/NVIDIA/cuda-python
Andy-Josthttps://github.com/Andy-Jost
NVIDIA:mainhttps://github.com/NVIDIA/cuda-python/tree/main
Andy-Jost:ajost/issue-2807https://github.com/Andy-Jost/cuda-python/tree/ajost/issue-2807
Conversationhttps://github.com/NVIDIA/cuda-python/pull/2871
Commits4 (4)https://github.com/NVIDIA/cuda-python/pull/2871/commits
Checkshttps://github.com/NVIDIA/cuda-python/pull/2871/checks
Files changedhttps://github.com/NVIDIA/cuda-python/pull/2871/files
cuda.core: fix the peer-access cleanup before pool destroyhttps://github.com/NVIDIA/cuda-python/pull/2871#top
Andy-Josthttps://github.com/Andy-Jost
NVIDIA:mainhttps://github.com/NVIDIA/cuda-python/tree/main
Andy-Jost:ajost/issue-2807https://github.com/Andy-Jost/cuda-python/tree/ajost/issue-2807
https://github.com/Andy-Jost
Andy-Josthttps://github.com/Andy-Jost
Sep 15, 2026https://github.com/NVIDIA/cuda-python/pull/2871#issue-5467926870
Please reload this pagehttps://github.com/NVIDIA/cuda-python/pull/2871
#2807https://github.com/NVIDIA/cuda-python/issues/2807
#1368https://github.com/NVIDIA/cuda-python/pull/1368
RAII resource handles for CUDA objects #1368https://github.com/NVIDIA/cuda-python/pull/1368
Claude Codehttps://claude.com/claude-code
Please reload this pagehttps://github.com/NVIDIA/cuda-python/pull/2871
https://github.com/Andy-Jost
https://github.com/claude
cuda.core: skip the pool's own device when clearing peer access at de…https://github.com/NVIDIA/cuda-python/pull/2871/commits/631ec7eec3cfa20f332b7e4d58dfdd172fd1c41a
631ec7ehttps://github.com/NVIDIA/cuda-python/pull/2871/commits/631ec7eec3cfa20f332b7e4d58dfdd172fd1c41a
NVIDIA#2807https://github.com/NVIDIA/cuda-python/issues/2807
https://github.com/Andy-Jost
Andy-Josthttps://github.com/Andy-Jost
cuda.core 1.3.0https://github.com/NVIDIA/cuda-python/milestone/52
Sep 15, 2026https://github.com/NVIDIA/cuda-python/pull/2871#event-31207090757
https://github.com/Andy-Jost
Andy-Josthttps://github.com/Andy-Jost
bug https://github.com/NVIDIA/cuda-python/issues?q=state%3Aopen%20label%3Abug
P1 https://github.com/NVIDIA/cuda-python/issues?q=state%3Aopen%20label%3AP1
cuda.core https://github.com/NVIDIA/cuda-python/issues?q=state%3Aopen%20label%3Acuda.core
Sep 15, 2026https://github.com/NVIDIA/cuda-python/pull/2871#event-31207090799
https://github.com/Andy-Jost
Andy-Josthttps://github.com/Andy-Jost
Sep 15, 2026https://github.com/NVIDIA/cuda-python/pull/2871#event-31207092395
https://github.com/Andy-Jost
Andy-Josthttps://github.com/Andy-Jost
leofanghttps://github.com/leofang
rluo8https://github.com/rluo8
September 15, 2026 22:57https://github.com/NVIDIA/cuda-python/pull/2871#event-31208853628
https://github.com/apps/github-actions
Sign in to viewhttps://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FNVIDIA%2Fcuda-python%2Fpull%2F2871
https://github.com/Andy-Jost
Andy-Josthttps://github.com/Andy-Jost
Sep 16, 2026 https://github.com/NVIDIA/cuda-python/pull/2871#ref-pullrequest-5479824073
[doc-only] ci: rebase concurrent gh-pages deployments instead of force-pushing #2883 https://github.com/NVIDIA/cuda-python/pull/2883
https://github.com/rluo8
rluo8https://github.com/rluo8
Sep 17, 2026 https://github.com/NVIDIA/cuda-python/pull/2871#pullrequestreview-5230642901
View reviewed changes https://github.com/NVIDIA/cuda-python/pull/2871/files/631ec7eec3cfa20f332b7e4d58dfdd172fd1c41a
rluo8https://github.com/rluo8
https://github.com/NVIDIA/cuda-python/pull/2871#pullrequestreview-5230642901
Learn morehttps://docs.github.com/articles/managing-disruptive-comments/#hiding-a-comment
Please reload this pagehttps://github.com/NVIDIA/cuda-python/pull/2871
Andy-Josthttps://github.com/Andy-Jost
September 17, 2026 08:58https://github.com/NVIDIA/cuda-python/pull/2871#commits-pushed-f1c6b82
https://github.com/Andy-Jost
https://github.com/claude
cuda.core: revoke pool peer access one device at a timehttps://github.com/NVIDIA/cuda-python/pull/2871/commits/f1c6b829f6e2583aa1e34daf39414491fa97ce21
f1c6b82https://github.com/NVIDIA/cuda-python/pull/2871/commits/f1c6b829f6e2583aa1e34daf39414491fa97ce21
NVIDIA#2807https://github.com/NVIDIA/cuda-python/issues/2807
https://github.com/Andy-Jost
Merge remote-tracking branch 'origin/main' into ajost/issue-2807https://github.com/NVIDIA/cuda-python/pull/2871/commits/4c341dca90c3c6f23a34adf255bc8bec1d0768dd
4c341dchttps://github.com/NVIDIA/cuda-python/pull/2871/commits/4c341dca90c3c6f23a34adf255bc8bec1d0768dd
https://github.com/Andy-Jost
Merge remote-tracking branch 'origin/main' into ajost/issue-2807https://github.com/NVIDIA/cuda-python/pull/2871/commits/b675687f0219a9337eb02bfc5426b749d8baaa4b
b675687https://github.com/NVIDIA/cuda-python/pull/2871/commits/b675687f0219a9337eb02bfc5426b749d8baaa4b
https://github.com/Andy-Jost
Andy-Josthttps://github.com/Andy-Jost
4490ecbhttps://github.com/NVIDIA/cuda-python/commit/4490ecbad66cb7d2f0125886115a9857ff4a0beb
Sep 17, 2026https://github.com/NVIDIA/cuda-python/pull/2871#event-31345968423
Please reload this pagehttps://github.com/NVIDIA/cuda-python/pull/2871
https://github.com/Andy-Jost
Andy-Josthttps://github.com/Andy-Jost
September 17, 2026 19:48https://github.com/NVIDIA/cuda-python/pull/2871#event-31345971460
https://github.com/apps/github-actions
github-actionshttps://github.com/apps/github-actions
Sep 17, 2026https://github.com/NVIDIA/cuda-python/pull/2871#issuecomment-5720597689
Please reload this pagehttps://github.com/NVIDIA/cuda-python/pull/2871
https://github.com/juenglin
juenglinhttps://github.com/juenglin
Sep 22, 2026 https://github.com/NVIDIA/cuda-python/pull/2871#ref-pullrequest-5542092075
fix(bindings): cover missing helper attrs and fix CU_JIT_WALL_TIME pointer #2931 https://github.com/NVIDIA/cuda-python/pull/2931
https://github.com/aryanputta
aryanputtahttps://github.com/aryanputta
Sep 24, 2026 https://github.com/NVIDIA/cuda-python/pull/2871#ref-pullrequest-5455440860
fix(cuda.core): clear peer access on recycled pools #2859 https://github.com/NVIDIA/cuda-python/pull/2859
https://github.co/hiddenchars
https://github.com/NVIDIA/cuda-python/pull/{{ revealButtonHref }}
Sign up for freehttps://github.com/join?source=comment-repo
Sign in to commenthttps://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FNVIDIA%2Fcuda-python%2Fpull%2F2871
https://github.com/rluo8
rluo8 https://github.com/rluo8
https://github.com/NVIDIA/cuda-python/pull/2871/files/631ec7eec3cfa20f332b7e4d58dfdd172fd1c41a
https://github.com/leofang
leofang https://github.com/leofang
Please reload this pagehttps://github.com/NVIDIA/cuda-python/pull/2871
https://github.com/Andy-Jost
Andy-Jost https://github.com/Andy-Jost
bug https://github.com/NVIDIA/cuda-python/issues?q=state%3Aopen%20label%3Abug
cuda.core https://github.com/NVIDIA/cuda-python/issues?q=state%3Aopen%20label%3Acuda.core
P1 https://github.com/NVIDIA/cuda-python/issues?q=state%3Aopen%20label%3AP1
cuda.core 1.3.0 https://github.com/NVIDIA/cuda-python/milestone/52
clear_mempool_peer_access() never takes effect: nvbug 5698116 workaround has been a no-op since #1368 https://github.com/NVIDIA/cuda-python/issues/2807
Please reload this pagehttps://github.com/NVIDIA/cuda-python/pull/2871
https://github.com/Andy-Jost
https://github.com/rluo8
https://github.com
Termshttps://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacyhttps://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Securityhttps://github.com/security
Statushttps://www.githubstatus.com/
Communityhttps://github.community/
Docshttps://docs.github.com/
Contacthttps://support.github.com?tags=dotcom-footer

Viewport: width=device-width

URLs of crawlers that visited me.