news
Red Hat Culls and Other Red Hat News
-
Bryan Lunduke ☛ Red Hat & FreeDesktop Go Into Mass Censorship Mode over Xorg Fork, Bans Dev
Immediately following news of the Xorg fork (Libre), the developer was banned by FreeDesktop and Red Bait mass closed hundreds of past Xorg merge requests.
-
Red Hat ☛ Optimize model serving at the edge with RawDeployment mode
The edge environment presents multiple challenges. Beyond the typical network connectivity limitations, there are other drawbacks to consider. As computing moves closer to the edge, the environment becomes more constrained. AI/ML processes often demand significant computational power and specialized hardware, which can be difficult to provide in an environment with limited space and resources. Additionally, edge locations often lack extensive dedicated IT support, requiring operations with minimal human intervention.
-
Red Hat ☛ Integrate vLLM inference on macOS/iOS with Llama Stack APIs
In the first article of this blog series, How to integrate vLLM inference into your macOS and iOS apps, I presented a business use case for integrating a finely tuned large language model (LLM), served by vLLM, with a chatbot that can run on macOS and iOS. That article introduced multiple options for connecting to vLLM's inference capabilities, including low-level HTTP communications with URLSession, general-purpose networking with Alamofire, and purpose-built libraries like SwiftOpenAI, MacPaw/OpenAI, and the llama-stack-client-swift SDK.