VP & GM - Red Hat AI Business Unit
Boston Area
Joined December 2007
- Tweets4K
- Following454
- Followers2.9K
- Likes2.9K
Joe Fernandes retweeted
Decades ago, critics questioned whether open source could meet enterprise security standards. Time and real-world adoption have since proven open source software as the powerhouse behind robust, resilient IT. We are seeing a similar evolution with AI today. Open-weight models offer vital flexibility, transparency, and defensive capabilities, making them an essential part of a secure AI ecosystem that is collaborative, transparent, and open. @RedHat is proud to sign this letter in support of open weights alongside @Microsoft and leaders across the industry. microsoft.com/en-us/corporat…
Joe Fernandes retweeted
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: red.ht/4lDjJ5P.
Joe Fernandes retweeted
.@_llm_d_ is a Kubernetes-native distributed LLM inference framework designed for fast, scalable serving across hardware accelerators with strong performance per dollar.
Learn how it works (and see a live demo) at this week’s @vllm_project office hours. Join details below 👇
ALT Learn about distributed LLM inference with llm-d
Joe Fernandes retweeted
Llama 4 Herd is here!
It brings a lot of goodies, like MoE architecture and native multimodality, enabling developers to build personalized multimodal experiences.
With Day 0 support in vLLM, you can deploy Llama 4 with @vllm_project now!
Let's dig into it.
(a thread)
Joe Fernandes retweeted
Quantization in the era of reasoning models: How does quantization impact the reasoning capabilities of DeepSeek-R1 models across distilled Llama and Qwen families?
👇 Check the thread for two surprising findings in evaluations of these models!
Joe Fernandes retweeted
[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 probabilistic-inference-scal…
Joe Fernandes retweeted
.@IBM's Granite models are known for efficiency and performance. Neural Magic team at @RedHat optimized them even further in Granite 3.1!
🪶 3.3x smaller
⚡ Up to 2.8x faster
🎯 99% accuracy retention
Here’s how these improvements unlock efficient open-source AI deployments 🧵
ALT Comparison of baseline and quantized versions of Granite 3.1 8B for inference benchmarks for RAG and code completion scenarios on 1xA6000 and 1xL40 GPUs for best latency (single-stream) and throughput (multi-stream) performance.
Joe Fernandes retweeted
Appreciate the partnership from @MichaelHanulec and the team at Goldman Sachs on this journey. @kubevirt and @openshift virtualization would not be what they are today without them!
Listening to @dummdida, a @kubevirt maintainer and Michael Hanulec from @GoldmanSachs talk about about their journey with #KubeVirt
Joe Fernandes retweeted
Breaking news 📰 @Gartner_inc places Red Hat as a Leader in the Magic Quadrant for Container Management. Read all about it: bit.ly/46iYS06 @OpenShift #Containers
Joe Fernandes retweeted
Great talk from Henrique Romao Oliveira from @BancoOriginal and Gabriel Sampaio from Red Hat talking about their work on Pix @openshiftcommon
Joe Fernandes retweeted
Good points @openshiftcommon from John Maciocci and Suresh Ganesan @CitizensBank about how you need to keep driving skill set and education once you have a platform in place to keep it successful.
“Taming the pets: Managing a heterogenous and sovereign multi-cloud container platform”. Long time @openshift customer Swiss Federal Railways talks about managing large fleet of #Kubernetes clusters across AWS, Azure and T-Systems Open Telekom Cloud @openshiftcommon @RedHatSummit
“Overcoming Fake Cloud in Telco” with @openshift. Great talk on the challenges of managing a multivendor 5G Cloud-native Network Function (CNF) workload environment by @SaskTel @openshiftcommon @RedHatSummit
“Safely Navigating Storm Clouds” with @openshift running containers and VMs across 100+ weather forecast office locations at National Oceanic and Atmospheric Association (NOAA). @openshiftcommon @RedHat
Joe Fernandes retweeted
.@Azure Red Hat @OpenShift’s modern, scalable architecture, enabled the development and deployment of @ExxonMobil #cloud-native applications at scale. See how they did it. red.ht/3MgZafz #RHSummit
Audi is using @openshift to enable their hybrid cloud strategy and “bring a startup mentality into the enterprise” @openshiftcommon @RedHatSummit
Advanced Auto Parts is using @openshift cloud services to help drive their application modernization efforts. @openshiftcommon @RedHatSummit
Listening to @rhatdan talk about bringing containerized WASM to cloud native platforms with @openshift #Kubernetes @openshiftcommon #RHSummit
In this blog, we’ll describe our high-performing, cloud-native AI training stack running on the @Red Hat @OpenShift Container Platform that serves as the foundation for the newly launched watsonx platform. research.ibm.com/blog/opensh…
