Models & Labs
Together AI Enhances Open-Weight Inference Platform
Together AI Bloghigh confidence
Why it matters
- →Provides developers with greater control over AI model deployment and performance.
- →Supports secure integration of proprietary IP with open-weight models.
- →Streamlines AI deployment with advanced features like canary and blue-green updates.
Together AI has launched a significant update to its inference platform, designed to give developers greater control over AI model deployment. The platform supports rapid model deployment with features like canary and blue-green updates, ensuring production-grade reliability. A closed beta for custom training, including reinforcement learning and fine-tuning, is also announced. This update emphasizes the use of open-weight models, allowing teams to integrate proprietary IP securely while maintaining control over performance and quality. The platform aims to streamline AI deployment, making it more flexible and efficient.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More in Models & Labs
Models & Labsother
llama.cpp b11193 adds Snapdragon Hexagon and ROCm 10
This release quietly expands llama.cpp's hardware support to include Qualcomm's Hexagon NPU on Linux arm64, a significant step for local inference on Snapdragon devices. It also updates CUDA builds to version 13.4 and introduces ROCm 10.0 binaries, keeping the project aligned with the latest NVIDIA and AMD driver ecosystems. KleidiAI on Apple Silicon is temporarily disabled in this build, likely due to stability checks rather than a feature rollback. For developers targeting edge AI or diverse GPU stacks, this update ensures broader compatibility without requiring custom compilation.
llama.cpp Releases
© Lev SelectorModels & Labsmodels
NVIDIA NVFP4 and SoL-Pi Token Efficiency
NVIDIA introduced the NVFP4 4-bit format and SoL-Pi technology, which uses 2x fewer tokens for improved efficiency.