home.social

#graviton — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #graviton, aggregated by home.social.

fetched live
  1. Today my Termix answered with a 404 this morning 🫠 CloudFront was fine, EC2 was fine (obviously since 404 was returned from nginx). There was just nothing behind it.

    Termix on :latest, the host updates everything at night, and by morning it was exit 1, restart, 1, restart.

    It is a Graviton box, so I went at the architecture first and the architecture was innocent. docker inspect said linux/arm64. Right image, right machine.

    The mismatch was inside it. better-sqlite3 ships a prebuilt binary linked against GLIBC 2.38 and the image has 2.36, so the linker refuses and node never starts.

    Pinned 2.6.1 and it came back (AWS Sessions Manager saved me).

    I put :latest there on purpose a year ago, FOMO, and because it is only a homelab. A homelab I route every other server through.

    ntfy has been sending me those logs every night. I read them.

    I am clearly going to keep reading them exactly the same way. The hard lesson learned.

    Bug Report is still open BTW: github.com/Termix-SSH/Support/

    #Linux #Docker #AWS #Graviton #SelfHosting #Blog #Thoughts #DevOps #Fediverse #Termix

  2. Today my Termix answered with a 404 this morning 🫠 CloudFront was fine, EC2 was fine (obviously since 404 was returned from nginx). There was just nothing behind it.

    Termix on :latest, the host updates everything at night, and by morning it was exit 1, restart, 1, restart.

    It is a Graviton box, so I went at the architecture first and the architecture was innocent. docker inspect said linux/arm64. Right image, right machine.

    The mismatch was inside it. better-sqlite3 ships a prebuilt binary linked against GLIBC 2.38 and the image has 2.36, so the linker refuses and node never starts.

    Pinned 2.6.1 and it came back (AWS Sessions Manager saved me).

    I put :latest there on purpose a year ago, FOMO, and because it is only a homelab. A homelab I route every other server through.

    ntfy has been sending me those logs every night. I read them.

    I am clearly going to keep reading them exactly the same way. The hard lesson learned.

    Bug Report is still open BTW: github.com/Termix-SSH/Support/

    #Linux #Docker #AWS #Graviton #SelfHosting #Blog #Thoughts #DevOps #Fediverse #Termix

  3. Today my Termix answered with a 404 this morning 🫠 CloudFront was fine, EC2 was fine (obviously since 404 was returned from nginx). There was just nothing behind it.

    Termix on :latest, the host updates everything at night, and by morning it was exit 1, restart, 1, restart.

    It is a Graviton box, so I went at the architecture first and the architecture was innocent. docker inspect said linux/arm64. Right image, right machine.

    The mismatch was inside it. better-sqlite3 ships a prebuilt binary linked against GLIBC 2.38 and the image has 2.36, so the linker refuses and node never starts.

    Pinned 2.6.1 and it came back (AWS Sessions Manager saved me).

    I put :latest there on purpose a year ago, FOMO, and because it is only a homelab. A homelab I route every other server through.

    ntfy has been sending me those logs every night. I read them.

    I am clearly going to keep reading them exactly the same way. The hard lesson learned.

    Bug Report is still open BTW: github.com/Termix-SSH/Support/

    #Linux #Docker #AWS #Graviton #SelfHosting #Blog #Thoughts #DevOps #Fediverse #Termix

  4. Today my Termix answered with a 404 this morning 🫠 CloudFront was fine, EC2 was fine (obviously since 404 was returned from nginx). There was just nothing behind it.

    Termix on :latest, the host updates everything at night, and by morning it was exit 1, restart, 1, restart.

    It is a Graviton box, so I went at the architecture first and the architecture was innocent. docker inspect said linux/arm64. Right image, right machine.

    The mismatch was inside it. better-sqlite3 ships a prebuilt binary linked against GLIBC 2.38 and the image has 2.36, so the linker refuses and node never starts.

    Pinned 2.6.1 and it came back (AWS Sessions Manager saved me).

    I put :latest there on purpose a year ago, FOMO, and because it is only a homelab. A homelab I route every other server through.

    ntfy has been sending me those logs every night. I read them.

    I am clearly going to keep reading them exactly the same way. The hard lesson learned.

    Bug Report is still open BTW: github.com/Termix-SSH/Support/

    #Linux #Docker #AWS #Graviton #SelfHosting #Blog #Thoughts #DevOps #Fediverse #Termix

  5. #Meta will use hundreds of thousands of #AWS #Graviton chips in its data centres for at least three years. This deal, alongside recent agreements with CoreWeave and Nebius, demonstrates Meta’s commitment to meeting high #computingdemands for #AIworkloads. Graviton chips will complement Meta’s existing use of Nvidia GPUs. cnbc.com/2026/04/24/meta-will- #tech #media #news

  6. #Meta will use hundreds of thousands of #AWS #Graviton chips in its data centres for at least three years. This deal, alongside recent agreements with CoreWeave and Nebius, demonstrates Meta’s commitment to meeting high #computingdemands for #AIworkloads. Graviton chips will complement Meta’s existing use of Nvidia GPUs. cnbc.com/2026/04/24/meta-will- #tech #media #news

  7. #Meta will use hundreds of thousands of #AWS #Graviton chips in its data centres for at least three years. This deal, alongside recent agreements with CoreWeave and Nebius, demonstrates Meta’s commitment to meeting high #computingdemands for #AIworkloads. Graviton chips will complement Meta’s existing use of Nvidia GPUs. cnbc.com/2026/04/24/meta-will- #tech #media #news

  8. #Meta will use hundreds of thousands of #AWS #Graviton chips in its data centres for at least three years. This deal, alongside recent agreements with CoreWeave and Nebius, demonstrates Meta’s commitment to meeting high #computingdemands for #AIworkloads. Graviton chips will complement Meta’s existing use of Nvidia GPUs. cnbc.com/2026/04/24/meta-will- #tech #media #news

  9. #Meta will use hundreds of thousands of #AWS #Graviton chips in its data centres for at least three years. This deal, alongside recent agreements with CoreWeave and Nebius, demonstrates Meta’s commitment to meeting high #computingdemands for #AIworkloads. Graviton chips will complement Meta’s existing use of Nvidia GPUs. cnbc.com/2026/04/24/meta-will- #tech #media #news

  10. Leyendo este artículo me entero (o confirmo) que al #x86-64 le están dando bien por culo comparado con #ARM en servidores también.

    #Amazon tiene su línea de ARM llamada #Graviton que lo usan en 98% de AWS. Flipa.

    elpais.com/economia/2026-04-11

  11. Leyendo este artículo me entero (o confirmo) que al #x86-64 le están dando bien por culo comparado con #ARM en servidores también.

    #Amazon tiene su línea de ARM llamada #Graviton que lo usan en 98% de AWS. Flipa.

    elpais.com/economia/2026-04-11

  12. Leyendo este artículo me entero (o confirmo) que al #x86-64 le están dando bien por culo comparado con #ARM en servidores también.

    #Amazon tiene su línea de ARM llamada #Graviton que lo usan en 98% de AWS. Flipa.

    elpais.com/economia/2026-04-11

  13. Leyendo este artículo me entero (o confirmo) que al #x86-64 le están dando bien por culo comparado con #ARM en servidores también.

    #Amazon tiene su línea de ARM llamada #Graviton que lo usan en 98% de AWS. Flipa.

    elpais.com/economia/2026-04-11

  14. Leyendo este artículo me entero (o confirmo) que al #x86-64 le están dando bien por culo comparado con #ARM en servidores también.

    #Amazon tiene su línea de ARM llamada #Graviton que lo usan en 98% de AWS. Flipa.

    elpais.com/economia/2026-04-11

  15. Anybody using #aws with #graviton nodes or instances? If so, what's your #development workflow? Do you use emulation? Do you have an arm-based development environment? Locally or #cloudBased? Do you support amd64 and arm64? What are you thoughts? #programming #devops #webdev #webdevelopment

    EDIT: Also #azure and #gcp users

  16. Anybody using #aws with #graviton nodes or instances? If so, what's your #development workflow? Do you use emulation? Do you have an arm-based development environment? Locally or #cloudBased? Do you support amd64 and arm64? What are you thoughts? #programming #devops #webdev #webdevelopment

    EDIT: Also #azure and #gcp users

  17. Anybody using #aws with #graviton nodes or instances? If so, what's your #development workflow? Do you use emulation? Do you have an arm-based development environment? Locally or #cloudBased? Do you support amd64 and arm64? What are you thoughts? #programming #devops #webdev #webdevelopment

    EDIT: Also #azure and #gcp users

  18. Anybody using #aws with #graviton nodes or instances? If so, what's your #development workflow? Do you use emulation? Do you have an arm-based development environment? Locally or #cloudBased? Do you support amd64 and arm64? What are you thoughts? #programming #devops #webdev #webdevelopment

    EDIT: Also #azure and #gcp users

  19. Anybody using #aws with #graviton nodes or instances? If so, what's your #development workflow? Do you use emulation? Do you have an arm-based development environment? Locally or #cloudBased? Do you support amd64 and arm64? What are you thoughts? #programming #devops #webdev #webdevelopment

    EDIT: Also #azure and #gcp users

  20. Physicists Begin Building First-Ever Graviton Detector

    Stevens Institute of Technology physicist Igor Pikovski and colleagues are developing the first experiment designed to capture individual…
    #NewsBeep #News #US #USA #UnitedStates #UnitedStatesOfAmerica #Physics #blackhole #gravitationalwaves #graviton #gravity #neutronstar #Science #supermassiveblackhole
    newsbeep.com/us/418644/

  21. Physicists Begin Building First-Ever Graviton Detector

    Stevens Institute of Technology physicist Igor Pikovski and colleagues are developing the first experiment designed to capture individual…
    #NewsBeep #News #Physics #BlackHole #gravitationalwaves #graviton #gravity #neutronstar #Science #supermassiveblackhole #UK #UnitedKingdom
    newsbeep.com/uk/380086/

  22. Physiker wollen erste Graviton-Falle konstruieren. Ultrakalter Resonator soll lange gesuchte Trägerteilchen der Gravitation nachweisen. #Gravitation #Graviton #Physik
    scinexx.de/news/physik/physike

  23. Physiker wollen erste Graviton-Falle konstruieren. Ultrakalter Resonator soll lange gesuchte Trägerteilchen der Gravitation nachweisen. #Gravitation #Graviton #Physik
    scinexx.de/news/physik/physike

  24. Physiker wollen erste Graviton-Falle konstruieren. Ultrakalter Resonator soll lange gesuchte Trägerteilchen der Gravitation nachweisen. #Gravitation #Graviton #Physik
    scinexx.de/news/physik/physike

  25. Physiker wollen erste Graviton-Falle konstruieren. Ultrakalter Resonator soll lange gesuchte Trägerteilchen der Gravitation nachweisen. #Gravitation #Graviton #Physik
    scinexx.de/news/physik/physike

  26. Physiker wollen erste Graviton-Falle konstruieren. Ultrakalter Resonator soll lange gesuchte Trägerteilchen der Gravitation nachweisen. #Gravitation #Graviton #Physik
    scinexx.de/news/physik/physike

  27. World’s first ‘graviton trap’ aims to solve century-old physics mystery

    Physicists from Stevens Institute of Technology and Yale University have launched an experimental program to detect gravitons —…
    #NewsBeep #News #Physics #AU #Australia #Energy&Environment #graviton #gravity #quantumparticles #Science #Space
    newsbeep.com/au/418879/

  28. World’s first ‘graviton trap’ aims to solve century-old physics mystery

    Physicists from Stevens Institute of Technology and Yale University have launched an experimental program to detect gravitons —…
    #NewsBeep #News #Physics #Energy&Environment #graviton #gravity #quantumparticles #Science #Space #UK #UnitedKingdom
    newsbeep.com/uk/374986/

  29. 🤖 Oh wow, #AWS rolled out #Graviton 5 and somehow we’re all supposed to be impressed by *yet another* alphabet soup instance: the #M9g 🤯. Apparently, you can achieve "incredible results" in just one week, which is *exactly* how long it takes to decipher AWS's #pricing 😜.
    aws.amazon.com/ec2/instance-ty #cloud #computing #tech #innovation #humor #HackerNews #ngated

  30. 🤖 Oh wow, #AWS rolled out #Graviton 5 and somehow we’re all supposed to be impressed by *yet another* alphabet soup instance: the #M9g 🤯. Apparently, you can achieve "incredible results" in just one week, which is *exactly* how long it takes to decipher AWS's #pricing 😜.
    aws.amazon.com/ec2/instance-ty #cloud #computing #tech #innovation #humor #HackerNews #ngated

  31. 🤖 Oh wow, #AWS rolled out #Graviton 5 and somehow we’re all supposed to be impressed by *yet another* alphabet soup instance: the #M9g 🤯. Apparently, you can achieve "incredible results" in just one week, which is *exactly* how long it takes to decipher AWS's #pricing 😜.
    aws.amazon.com/ec2/instance-ty #cloud #computing #tech #innovation #humor #HackerNews #ngated

  32. 🤖 Oh wow, #AWS rolled out #Graviton 5 and somehow we’re all supposed to be impressed by *yet another* alphabet soup instance: the #M9g 🤯. Apparently, you can achieve "incredible results" in just one week, which is *exactly* how long it takes to decipher AWS's #pricing 😜.
    aws.amazon.com/ec2/instance-ty #cloud #computing #tech #innovation #humor #HackerNews #ngated

  33. every percentage point of efficiency = better customer experience + lower costs + fewer resources burned. if you're running compute-intensive stuff on AWS and haven't kicked the tyres on #Graviton yet, worth looking at. preview signup here: aws.amazon.com/ec2/instance...

    Amazon EC2 M9g instances

  34. every percentage point of efficiency = better customer experience + lower costs + fewer resources burned. if you're running compute-intensive stuff on AWS and haven't kicked the tyres on #Graviton yet, worth looking at. preview signup here: aws.amazon.com/ec2/instance...

    Amazon EC2 M9g instances

  35. every percentage point of efficiency = better customer experience + lower costs + fewer resources burned. if you're running compute-intensive stuff on AWS and haven't kicked the tyres on #Graviton yet, worth looking at. preview signup here: aws.amazon.com/ec2/instance...

    Amazon EC2 M9g instances

  36. every percentage point of efficiency = better customer experience + lower costs + fewer resources burned. if you're running compute-intensive stuff on AWS and haven't kicked the tyres on #Graviton yet, worth looking at. preview signup here: aws.amazon.com/ec2/instance...

    Amazon EC2 M9g instances

  37. The is a hypothetical elementary particle that mediates the force of gravity.

    While it hasn't been directly observed yet, it plays a significant role in theories of .

    knowledgezone.co.in/kbits/6524

  38. The #Graviton is a hypothetical elementary particle that mediates the force of gravity.

    While it hasn't been directly observed yet, it plays a significant role in theories of #Quantum #Gravity.

    knowledgezone.co.in/kbits/6524

  39. The #Graviton is a hypothetical elementary particle that mediates the force of gravity.

    While it hasn't been directly observed yet, it plays a significant role in theories of #Quantum #Gravity.

    knowledgezone.co.in/kbits/6524

  40. The #Graviton is a hypothetical elementary particle that mediates the force of gravity.

    While it hasn't been directly observed yet, it plays a significant role in theories of #Quantum #Gravity.

    knowledgezone.co.in/kbits/6524

  41. The #Graviton is a hypothetical elementary particle that mediates the force of gravity.

    While it hasn't been directly observed yet, it plays a significant role in theories of #Quantum #Gravity.

    knowledgezone.co.in/kbits/6524

  42. Как мы ускорили ввод новых узлов до 40 секунд: надежная работа на spot-инстансах в Kubernetes с Karpenter

    В нашей практике DevOps мы столкнулись с задачей оптимизации Kubernetes-кластера в AWS, включая перевод нагрузки на ARM64-инстансы с процессорами Graviton и эффективное использование spot-инстансов. Благодаря Amazon EKS и Karpenter нам удалось ускорить ввод новых узлов до всего 40 секунд и успевать переносить нагрузку при отборе узлов со стороны AWS. При этом мы сохранили привычный набор инструментов Deckhouse для мониторинга и управления — статья подробно рассказывает о нашем опыте и решениях.

    habr.com/ru/companies/flant/ar

    #kubernetes #karpenter #eks #amd64 #nodepool #optimization #graviton #оптимизация #spot_instances #spotинстанс