Expert Guide: Installing Ollama LLM with GPU on AWS in Just 10 Mins

Поделиться
HTML-код
  • Опубликовано: 24 янв 2025

Комментарии • 30

  • @fastandsimpledevelopment
    @fastandsimpledevelopment  11 месяцев назад +3

    Need a heavy GPU machine? Check out this video on setting AWS EC2 GPU instance. If you like this one check out my video on setting up a full RAG API with Llama3, Ollama, Langchain and ChromaDB - ruclips.net/video/7VAs22LC7WE/видео.html

  • @alphistube1077
    @alphistube1077 17 дней назад +1

    Bro ❤ great tutorial. Quick and easy

  • @joshwaphly
    @joshwaphly 4 месяца назад +4

    OMG!!! I freaking love you, I've been struggling with deployment on AWS with llama and you've made it crystal clear. I'll do anything to support ur channel. UR THE BEST!!!

  • @christague2084
    @christague2084 10 месяцев назад +1

    Cannot wait for part two with LangChain! This video was fantastic

  • @ExpertKNowledgeGroup
    @ExpertKNowledgeGroup 11 месяцев назад

    What a simple way to setup Ollama LLM with GPU support in only a few minutes, thanks!

  • @sahillakhe1093
    @sahillakhe1093 5 месяцев назад +1

    Briliant! Its that simple only because you explained it simply :). Thank you!

  • @prodbyindigo
    @prodbyindigo 2 месяца назад +1

    I'm not sure if you mentioned in the video or not but you need to allow traffic to port 11434 on the AWS security group

  • @bingbingxv
    @bingbingxv 10 месяцев назад

    Thank you so much! Your video helps me a lot. I am looking forward to your new video.

  • @danilchurko2882
    @danilchurko2882 8 месяцев назад +1

    Thanks man a lot! Great video!

  • @hebertgodoy5039
    @hebertgodoy5039 7 месяцев назад

    Excellent. Thank you very much for sharing.

  • @paulluka7594
    @paulluka7594 8 месяцев назад +1

    Thanks a lot for the video !!
    Question : Is it possible to start the instance only if we do a request to the server ? It can be usfull to limit the costs.
    I think it is feasable with kubernetes and docker, but i would enjoy a video about it :) !
    Thnks again, very good video

  • @sachin1250
    @sachin1250 8 месяцев назад

    How to add openwebui to it, and expose the openwebui to be accessible from macbook browser?

  • @123arskas
    @123arskas 10 месяцев назад

    Thank you. This was helpful

  • @Gerald-iz7mv
    @Gerald-iz7mv 10 месяцев назад +1

    can you also use the ubuntu 22.04 image and install cuda etc? why use this deep learning image?

    • @fastandsimpledevelopment
      @fastandsimpledevelopment  9 месяцев назад

      I only select this AMI since it already has teh other code I need like Python

    • @Gerald-iz7mv
      @Gerald-iz7mv 9 месяцев назад

      @@fastandsimpledevelopment if i correctly understand you can select the base ubuntu 22.04 image and install all yourself: nvidia driver, cuda driver, tensorflow, python etc?

  • @yashshinde8185
    @yashshinde8185 6 месяцев назад

    The Video was awesome and prety helpful but can you cover the security point of view too like anyone with the IP and portnumber can access it So how can we avoide that?

  • @pushkarpadmnav
    @pushkarpadmnav 9 месяцев назад +1

    How do you make it scalable ?

    • @fastandsimpledevelopment
      @fastandsimpledevelopment  9 месяцев назад

      By itself it is not, you need to add a front end like Nginx and then have several Ollama servers running, that is the only way that I am aware today. There is new updates all the time to keep track of Ollama updates

  • @adityanjsg99
    @adityanjsg99 3 месяца назад

    So ollama detects and uses the GPU automatically?

    • @fastandsimpledevelopment
      @fastandsimpledevelopment  3 месяца назад

      Yes, if the OS has support and you have an AMD or Nvidia GPU installed and the latest version does auto-detect. You can also set it to NOT use the GPU in the Ollama config files but by default it does auto-detect.

    • @adityanjsg99
      @adityanjsg99 2 месяца назад +1

      @@fastandsimpledevelopment It detects only Nvidia GPU. I tried on AWS g4ad (AMD ) and g4dn.xlarge (Nvidia). Only the latter worked. This is FYI.

    • @fastandsimpledevelopment
      @fastandsimpledevelopment  2 месяца назад

      @@adityanjsg99 Thanks for your input. I have not tried anything other than NVidia GPU's, I've finally decided to get a few 4090 boards and see how they run. I'm trying to build an on-prem system since there is no affordable cloud solution. I'll externalize the LLM API via ngrok, not what I wanted :(

  • @ctoxyz
    @ctoxyz 8 месяцев назад

    good vid!

  • @blackalert.agency
    @blackalert.agency 9 месяцев назад

    thanks buddy

  • @emineyoubah7418
    @emineyoubah7418 9 месяцев назад

    Cannot wait for part two with LangChain! This video was fantastic