Mofi Rahman
@moficodes
Followers
895
Following
2K
Media
245
Statuses
1K
Developer Advocate @google. Previously @vonage @IBM. Love Go + Kubernetes. Views are my own. 🦋 @mofi.dev
New York, USA
Joined January 2016
RT @ThomasOrTK: Today, we introduced Gemini CLI, an open-source AI agent that empowers developers with a versatile, local utility that can….
0
61
0
I am looking forward to some fun discussions around Kubernetes, the conference, ecosystem, past present and future of cloud native.
🚀 Don't forget to dial in for our livestream from KubeCon + CloudNativeCon EU 2025 in London 🇬🇧this week. We will be live-streaming a daily recap from the event. Check the dates/hours below 👇. #KubernetesPodcast #Livestream #Kubernetes
0
0
1
RT @boredabdel: We will be live from #KubeConEU25 tomorrow with @moficodes and the @KubernetesPod and every day for a daily recap of the ev….
0
1
0
RT @boredabdel: Putting the final touches on our session at #KubeConNA 🙌. Join us in room 255B at 11:55AM for an introduction to distribute….
0
2
0
RT @gusthema: Hey everyone! 👋 Guess what? .💎Gemma 2 (9B)💎 is now available on Google AI Studio!. Go play around with it and let me know wha….
0
4
0
RT @nicholaseberts: I really like the approach we took to improve scalability of GKE. Rather than building a non idiomatic feature (Glares….
0
2
0
RT @_techcet_: Using Ray for your AI/ML workloads? Learn how to secure them on GKE with the fresh off the press #ContainerBytes episode wit….
www.youtube.com
As a distributed compute framework for AI applications, Ray has grown in popularity in recent years, and deploying it on GKE is a popular choice that provide...
0
3
0
We wanted to make sure we have a number of different ways to access the model. There is c++ version, a notebook that you can run on colab for free. The model is available for download on Huggingface or Kaggle. Excited to see what we can do with finetuning and RAG.
0
0
1
4. SaxML with TPUs -
cloud.google.com
Serve Gemma (open model) large language models (LLM) using TPUs on GKE with Saxml
1
0
2
Want to try running Gemma on GKE? We made a bunch of different docs to help you do just that. 1. TGI with GPUs -
cloud.google.com
Deploy Gemma large language models (LLMs) using GPUs on GKE with the Text Generation Inference (TGI) serving framework from Hugging Face.
1
2
4
RT @lukeschlangen: Why does the kubernetes logo look like that? . If you want more ridiculousness from me and more actual substantive conte….
0
4
0
RT @GroschStefan: Check out this new YT channel launched by @moficodes and @lukeschlangen. aim to make containers and Kubernetes easy to un….
google.smh.re
Containers and Kubernetes can be complex. So Luke Schlangen and Mofi Rahman, with the help and support of rest of the GKE DevRel team created a channel on youtube where we will try to make it...
0
2
0
RT @sshunmuganathan: Check out this new YT channel launched by @moficodes and @lukeschlangen. aim to make containers and Kubernetes easy to….
google.smh.re
Containers and Kubernetes can be complex. So Luke Schlangen and Mofi Rahman, with the help and support of rest of the GKE DevRel team created a channel on youtube where we will try to make it...
0
2
0
RT @kaslinfields: My teammates @moficodes and @lukeschlangen started a new YouTube channel for container content called Container Bytes! It….
www.youtube.com
Containers can be complex. We are here to make it simple one byte at a time.
0
4
0