Chris Wright
@kernelcdub
Followers
7K
Following
4K
Media
88
Statuses
2K
Red Hat CTO. Tezos Foundation council member. Passion for open source SW innovation. Father and husband. Cyclist. Human.
Boston, MA
Joined May 2012
RT @RedHat: Ever wonder what the 'v' in vLLM stands for? 💡 @kernelcdub and @nickhill33 explain how "virtual" memory and PagedAttention make….
0
10
0
Nick Hill digs into the details of vLLM with me on Technically Speaking. Helpful in understanding why vLLM is so important in high performance, open source AI inferencing.
How do you solve AI's biggest performance hurdles? On Technically Speaking, @kernelcdub & Nick Hill dive into vLLM, exploring how techniques like PagedAttention solve memory bottlenecks & accelerate inference:
1
5
12
Great discussion with @AMD about how we see future of AI and the importance of openness and choice.
The future of AI is being built on openness, efficiency, and choice, and AMD is helping make it possible. Chris Wright, CTO and SVP at @RedHat, explains the state of AI. Open AI is accelerating - from open source frameworks to open LLMs that now match or even exceed
0
0
11
It's tools, it's models, it's agents. the future of #AI is open source and collaboration. We have to build this together.
"The future of AI is going to be open sourced." . In this clip, @kernelcdub of @RedHat explains why open source, open collaboration, and global ecosystems will define the next wave of AI, and how Red Hat empowers developers everywhere
0
0
6
Rapid fire buzzword decoding with @addvin.
What's the first thing that comes to mind when tech leaders hear today's top AI & enterprise buzzwords? 🤔 Watch Red Hat CTO @kernelcdub & AI CTO @addvin tackle them in a quick-fire word association game! Don't miss the latest episode of Technically Speaking 🎙️for their deep-dive
0
1
6
Hope you enjoy this great discussion I had with @addvin on Technically Speaking. The future of open source AI inference!.
AI Inference at scale? 🤔 Open source to the rescue! 💡 Dive into #vLLM, distributed systems, and the path to practical #AI in the enterprise with @kernelcdub and @addvin on the latest "Technically Speaking."
1
8
21
Nice nod to Ramalama here. containers to make AI easy (aka boring):
0
1
9
Here's how we're achieving R1 like reasoning with small models leveraging probabalistic inference-time scaling w/out using DeepSeek or derivatives. Results are impressive! MATH w/ Llama 8B approaches GPT-4o, and w/ Qwen2.5 Math 7B Instruct hits o1 level.
1
9
28
Inference-time scaling brings smaller LLMs to o1 level capabilities. This is why we're so excited about the potential of smaller, open source models. Awesome work @ishapuri101 and @RedHat AI Innovation team!.
[1/x] can we scale small, open LMs to o1 level? Using classical probabilistic inference methods, YES! Joint @MIT_CSAIL / @RedHat AI Innovation Team work introduces a particle filtering approach to scaling inference w/o any training! check out
0
6
18
Nice example of getting started with Triton on AMD GPUs. torch.compile and start playing around!
0
0
3
RT @RedHat: We agree, @kernelcdub: the future of AI is open source 👐 Onsite at #AWSreInvent? Stop by booth #844 to see how you can transfor….
0
8
0
Nov 19 join us for #RHOpenTelco 2024! Discover how #AI, automation & open networks are transforming #telecom. I love hearing the insights from industry leaders. And come check out my keynote. Save the date!
0
1
4
Exciting news! @NeuralMagic’s technology is democratizing access to AI, just as InstructLab does for how we train and tune models. Shared origin stories, beliefs, and approaches underpin Red Hat's definitive agreement to acquire Neural Magic:
0
10
34
Love @kelseyhightower's response. The way #kubernetes and #linux communities complement one another.
Who's the bigger rock star in the industry: Kubernetes @KelseyHightower or @KernelCDub? 🎸🤘 . If you're onsite at #KubeCon + #CloudNativeCon this week, stop by booth #D1 to see why #Kubernetes depends on #Linux:
0
1
16
Very cool to make the @FastCompany list of World Changing Ideas 2024 with @KeplerProject showing power consumption to improve sustainable computing practices.
@FastCompany See how we're quantifying the footprint of the cloud with the open source project, Kepler: @KeplerProject.
1
1
14
Love seeing the #Kepler project getting this kind of visibility for its focus on sustainable computing:
1
3
8
Stoked on what's possible with InstructLab and really opening up AI:
6
24
61
I'm looking forward to this, always fun to discuss the evolution of #technology and #opensource at #RHSummit!.
Discover new perspectives on the current and future #technology landscape. Hear from @kernelcdub at his Red Hat Summit keynote speech: #RHSummit
2
6
26