Models & Labs
Gemini API Introduces Webhooks for Long-Running Jobs
Google AI Bloghigh confidence
Why it matters
- →Webhooks reduce the need for inefficient polling, saving resources and time.
- →Secure and reliable communication is ensured with signed requests and retries.
- →Developers can manage complex workflows more efficiently with real-time notifications.
Google has enhanced its Gemini API by introducing event-driven Webhooks, aimed at improving efficiency for long-running tasks. This new feature allows developers to receive immediate notifications when a job is completed, replacing the need for continuous polling. The Webhooks implementation is secure, adhering to the Standard Webhooks specification, and includes features like signed requests and automatic retries. This update is designed to support complex workflows, making it easier for developers to manage tasks such as deep research and batch processing.
Read originalMore from Google AI Blog
More in Models & Labs
Models & Labsmodels
Llama.cpp adds GLM-5.2 speculative decoding support
Llama.cpp's latest update introduces speculative decoding support for GLM-5.2, enhancing its capabilities with NextN/MTP features. This addition allows for more efficient tensor loading and context management, particularly benefiting models using the GLM_DSA architecture. The update also includes options for exporting models with or without the MTP feature, providing flexibility for developers. This release marks a step forward in optimizing model performance and adaptability, especially for those leveraging the GLM-5.2 framework.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b10178 Release Adds Trace Logging
The b10178 release of llama.cpp enhances its server capabilities by adding trace logging for slot similarity checking, offering developers detailed insights into prompt cache slot selection processes. This update includes specifics on skip reasons and similarity calculations, which can aid in performance optimization. While no new model architectures are introduced, the release continues to support a wide array of platforms, such as macOS with KleidiAI, Ubuntu with ROCm 7.2, and Windows with CUDA 12 and 13. This makes llama.cpp a more versatile tool for developers working on different systems, reinforcing its position as a comprehensive inference runtime.