October 19: @RedHat, @NVIDIA AI, and @IBM are hosting “PyTorch, Powering the Enterprise,” a #PyTorchCon# North America Day 0 event. The in-person event will explore PyTorch and the ecosystem shaping the future of enterprise AI. PyTorch and technologies across the ecosystem like @vllm_project, @raydistributed, Helion, and @_llm_d_ have become foundational to the AI stack, moving from research labs into production at some of the world’s largest enterprises. Attendees will hear from and interact with the companies helping to bring PyTorch to its full enterprise potential, with conversations spanning AI infrastructure, deployment, security, and the open source ecosystem. 🔗 Learn more and register: 🔗 Register for #PyTorchCon# NA:

Arm and @RedHat are expanding their collaboration to advance agentic AI infrastructure! By combining Arm AGI CPUs with Red Hat’s open source platforms we're enabling scalable, efficient performance for Agentic AI systems that plan, reason and act across cloud and on-prem environments. 🚀

Supermicro is simplifying Edge AI deployments with validated Kubernetes solutions powered by @RedHat and @EverpureData! By combining Supermicro's edge computing infrastructure with Red Hat OpenShift and the Portworx by Everpure data management platform for AI workloads, organizations can more easily deploy, manage, scale, and secure AI applications across distributed edge environments. Check out the full post by @storagereview:

The @vllm_project & llm-d maintainers at @RedHat_AI are some of the hardest-working and leading experts on inference in the world 🚀 Everyone in the ML community can tell you how kind & helpful @robertshaw21 & @mgoin_ are. We’re grateful to occasionally collaborate with them. ❤️

🚨 SlowMist TI Alert 🚨 MistEye has detected an active npm supply-chain attack compromising @redhat-cloud-services packages. Reported impact includes 31+ affected packages, about 116,282 weekly downloads, and 300+ GitHub repositories containing stolen credentials. The attack techniques show strong similarities to the previous Shai-Hulud npm campaign, including credential harvesting, malicious repository creation, and automated secret exfiltration. Public GitHub searches for the “Miasma: The Spreading Blight” marker, sorted by recent updates, still show newly appearing suspicious repositories, indicating that users are still being compromised. Potential attacker actions include GitHub/npm token theft, AWS/GCP/Azure credential theft, SSH key and Kubernetes secret collection, local environment and wallet data exfiltration, malicious GitHub repository creation, persistence, and destructive behavior if stolen tokens are revoked. Immediately remove or downgrade affected @redhat-cloud-services package versions, audit CI/CD workflows and dependency installs, rotate GitHub, npm, cloud, SSH, and wallet-related secrets, preserve logs, and rebuild exposed developer machines or runners from clean images. As always, stay vigilant! Live hunt:

New short course: Fast & Efficient LLM Inference with vLLM, built in partnership with @RedHat and taught by @cedricclyburn. Learn to quantize an open-source LLM, serve it with vLLM, and benchmark your deployment across speed, cost, and accuracy. Free to enroll:

Modernization doesn’t look the same for every organization. That’s why @RedHat trusts AMD. Together, we’re building an open, flexible foundation that lets you scale workloads across data center, hybrid, and multi-cloud environments with consistency, performance, and control. See how the most trusted companies trust AMD:

PyTorch moved from research labs to running enterprise AI. On Monday Oct 19, @RedHat, @NVIDIAAI, and @IBM host a day in San Jose: @vllm_project economics, @_llm_d_ at scale, and agents in production, with the @PyTorch maintainers behind them. Register:

PyTorch Conference is where the open source Al community gathers to talk about what we are all building together. Priya Nagpurkar, VP of AI Native Systems at @IBMResearch will give a keynote at #PyTorchCon# North America on @IBM & @RedHat's contributions to the PyTorch ecosystem, including exciting developments on infrastructure for out-of-tree accelerators, enablement of IBM's Spyre Accelerator, and work with Ilm-d for distributed inference. Come to the talk, meet the community, and hear what's next in open source Al. Join us in San Jose, October 20-21: