Deploying machine learning models on Kubernetes

แชร์
ฝัง
  • เผยแพร่เมื่อ 28 ธ.ค. 2024

ความคิดเห็น • 52

  • @ludwigstumpp
    @ludwigstumpp ปีที่แล้ว +7

    Always a pleasure to watch someone as talented as you! Keep it up :)

  • @abdjanshvamdjsj
    @abdjanshvamdjsj ปีที่แล้ว +9

    Brooooo this was so good.

  • @vishalgoklani
    @vishalgoklani ปีที่แล้ว +1

    Welcome back, we missed you!

  • @humanity-indian
    @humanity-indian 7 หลายเดือนก่อน +1

    Great example. Thanks for the information

  • @kwang-jebaeg2460
    @kwang-jebaeg2460 ปีที่แล้ว

    OH !!!!! Glad to meet you again !!!!

  • @thinkman2137
    @thinkman2137 ปีที่แล้ว +1

    Thank you for detail tutorial!

    • @thinkman2137
      @thinkman2137 ปีที่แล้ว

      But torchserve now has kubernetes intergration

    • @mildlyoverfitted
      @mildlyoverfitted  ปีที่แล้ว

      I will definitely look into it:) Thank you for pointing it out!!

  • @shivendrasingh9759
    @shivendrasingh9759 7 หลายเดือนก่อน +1

    Really helpful for foundation on ml ops

  • @aditya_01
    @aditya_01 11 หลายเดือนก่อน +1

    great video thanks a lot really liked the explanation !!!.

  • @fizipcfx
    @fizipcfx ปีที่แล้ว +2

    he is back 🎉

  • @unaibox1350
    @unaibox1350 ปีที่แล้ว +1

    Amazing video. In min 5:25 how did you do to open the second bash in the console? I was searching for a long time and I can't find anything. Thanks and regards!

    • @mildlyoverfitted
      @mildlyoverfitted  ปีที่แล้ว +1

      Thank you! You need to install a tool called tmux. One of its features is that you can have multiple panes on a single screen.

    • @unaibox1350
      @unaibox1350 ปีที่แล้ว +1

      @@mildlyoverfitted Thank you! Will dig in it now

  • @JoseMiguel_____
    @JoseMiguel_____ ปีที่แล้ว +1

    You're great. Thanks for sharing this in such a nice way.

  • @davidyates4857
    @davidyates4857 ปีที่แล้ว +1

    Great video very informative.

  • @maksim3285
    @maksim3285 ปีที่แล้ว +1

    Thank you, it helped me a lot .

  • @ivanxiecornell
    @ivanxiecornell ปีที่แล้ว +3

    Would appreciate a video using VScode to include docker contain files, k8s file and Fast API

  • @unaibox1350
    @unaibox1350 ปีที่แล้ว

    I am having a problem in the min 18:00 the model load is being killed all the time. I tried to "minikube config set memory 4096" but still having the same problem. Any idea? I've been looking for a solution for 3 hours and there is no way

    • @mildlyoverfitted
      @mildlyoverfitted  ปีที่แล้ว

      Hm, I haven't had that problem myself. However, yeh, it might be related to the lack of memory.

  • @SmiteLax
    @SmiteLax หลายเดือนก่อน

    Cheers mate!

  • @davidpratr
    @davidpratr 10 หลายเดือนก่อน

    really nice video. Would you see any benefit of using the deployment in a single node with M1 chip? I'd say somehow yes because an inference might not be taking all the CPU of the M1 chip, but how about scaling the model in terms of RAM? one of those models might take 4-7GB of RAM which makes up to 21GB of RAM only for 3 pods. What's you opinion on that?

    • @mildlyoverfitted
      @mildlyoverfitted  10 หลายเดือนก่อน +1

      Glad you liked the video! Honestly, I filmed the video on my M1 using minikube mostly because of convenience. But on real projects I have always worked with K8s clusters that had multiple nodes. So I cannot really advocate for the single node setup other than for learning purposes.

    • @davidpratr
      @davidpratr 9 หลายเดือนก่อน +1

      @@mildlyoverfittedgot it. So, very likely more petitions could be resolved at the same time but with a very limited scalability and probably with performance loss. By the way, what are those fancy combos with the terminal? is it tmux?

    • @mildlyoverfitted
      @mildlyoverfitted  9 หลายเดือนก่อน +1

      @@davidpratr interesting:) yes, it is tmux:)

  • @bpac90
    @bpac90 3 หลายเดือนก่อน

    excellent!! I'm curious why my search always shows garbage and videos like this never come up. This was suggested by Gemini when I asked a question about ML model deployment.

  • @johanngerberding5956
    @johanngerberding5956 ปีที่แล้ว

    very cool video!

  • @zhijunchen1248
    @zhijunchen1248 ปีที่แล้ว +1

    Hi, I would like to use GPU to accelerate this demo, can you give me some tips? Thank you

    • @mildlyoverfitted
      @mildlyoverfitted  ปีที่แล้ว

      So if you wanna use minikube this seems to be the solution. minikube.sigs.k8s.io/docs/handbook/addons/nvidia/

    • @zhijunchen1248
      @zhijunchen1248 ปีที่แล้ว +1

      @@mildlyoverfitted thankyou, i use the "--device" flag of transformers-cli to enable GPU. And I found that serving app takes up almost gpu memory and no compute power. Whatever, thankyou for your video!

  • @alivecoding4995
    @alivecoding4995 ปีที่แล้ว

    What terminal application is this, with the different panels?

  • @lauraennature
    @lauraennature ปีที่แล้ว

    New video 🤩

  • @EvaKreplova
    @EvaKreplova ปีที่แล้ว

    Great!

  • @nehetnehet8109
    @nehetnehet8109 ปีที่แล้ว

    Realy goood

  • @evab.7980
    @evab.7980 ปีที่แล้ว

    👏👏👏

  • @nehetnehet8109
    @nehetnehet8109 ปีที่แล้ว

    Great

  • @kwang-jebaeg2460
    @kwang-jebaeg2460 ปีที่แล้ว +1

    Look forward to show your face alot :))

  • @SunilSamson-w2l
    @SunilSamson-w2l 5 หลายเดือนก่อน

    the reason you got . , ? as the output for [MASK] because you didn't end your input request with a full stop. Bert Masking Models should be passed that way. "my name is [MASK]." should have been your request.