
Brian Gracely
@bgracely
Work: @RedHat
Hobby: Host @CloudcastPod ☁️🎙️
Misc: @WakeBaseball alum 🎩⚾️
Also now on @bgracely.bsky.social
ID: 14055566
http://thecloudcast.net 28-02-2008 17:10:59
32,32K Tweet
10,10K Followers
3,3K Following



LLM Compressor is the go-to library for optimizing LLMs for efficient, low-latency inference. AI at Meta recently used it to create FP8 versions of their Llama 4 Maverick model. Here’s a thread on what LLM Compressor is, its features, and how to use it to optimize your LLMs:


Red Hat AI AI at Meta There are over 400 models quantized with llm-compressor that are ready to deploy with vLLM Each model card has full reproducible creation and evaluation instructions. Give it a try! huggingface.co/RedHatAI



Yesterday, NVIDIA CEO Jensen Huang hosted the opening keynote at Computex in Taiwan. Excited to see Red Hat AI & Red Hat OpenShift featured prominently at the launch of AI Factory as references for k8s and AI platform. To watch the keynote, go here: nvidia.com/en-tw/gtc/keyn…



#RHSummit is LIVE now 🚨 Join #theCUBE’s Rob Strechay at 2025 & rebecca m. knight with Chris Wright to dig into Red Hat’s upcoming #OpenSource #AICommunityProjects – vLLM, llm-d, PyTorch and more! 📺 Tune in NOW! thecube.net/events/red-hat… #CTOInsights #EnterpriseTechNews #LiveNews

Universal Data Representation for AI bit.ly/cloudcast-925 Joel Christner, (Joel Christner, Founder/CEO at View Systems) discusses the complexities of data management in AI, structured and unstructured data, the importance of RAG pipelines and vector databases.





Preventing AI Hallucinations bit.ly/cloudcast-927 Anand Kannappan (Anand Kannappan, CEO PatronusAI) talks about evaluating AI models for hallucinations, managing data quality, automating the process, and optimizing models.


Join #theCUBE’s Rob Strechay at 2025 in this #RHSummit wrap up discussion with Stuart Miniman & Brian Gracely, as they compare this year’s event with last year’s & dig into what has changed for Red Hat. 📺 Catch the interviews on-demand! thecube.net/events/red-hat… #EnterpriseAI #EnterpriseTechNews

Love this approach by Red Hat AI. We need more trust & validation in AI and this can help! huggingface.co/RedHatAI




AI & Cloud Trends for May 2025 bit.ly/cloudcast-929 Brian Gracely (Brian Gracely) and Brandon Whichard (Brandon Whichard, SoftwareDefinedTalk) discuss the top stories in Cloud and AI from May 2025, including Google I/O, Microsoft Build, OpenAI, and Jony Ive.

