Models & Labs
Hugging Face Models Now on Microsoft Foundry
Hugging Face Bloghigh confidence
Why it matters
- →Provides enterprise-grade deployment for open-source models.
- →Enhances accessibility and usability of Hugging Face models in professional settings.
- →Bridges the gap between open AI innovation and enterprise infrastructure.
Microsoft Foundry has expanded its platform to include Hugging Face models, providing a comprehensive solution for deploying open-weight models in enterprise settings. This integration allows developers to access a curated selection of Hugging Face models, which are security-screened and optimized for enterprise use. Foundry's managed compute services ensure that these models can be deployed efficiently, with automatic updates and integration into existing enterprise systems. This collaboration enhances the accessibility of open-source models for professional use, offering a seamless path from model selection to deployment.
Read originalMore in Models & Labs
Models & Labsmodels
llama.cpp b10955 release addresses heap corruption
The latest release of llama.cpp, b10955, tackles a critical issue of heap corruption by disabling the ggml-cpu precompiled header and fixing CACHE_LINE_SIZE ambiguity. This update ensures consistent CACHE_LINE_SIZE values across C++ kernels and C work-buffer sizing code, preventing heap-buffer-overflow and subsequent crashes. By restoring the natural include order and removing the std::hardware_destructive_interference_size branch, the update makes the value deterministic and include-order independent. This release is a technical fix that stabilizes the runtime environment for developers using llama.cpp.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10956 release enhances SYCL backend
The latest llama.cpp release, b10956, introduces significant improvements to the SYCL backend, particularly for handling large k values in TOP_K operations. By implementing a radix select method, the update allows for efficient GPU-resident processing, avoiding previous limitations that forced operations to fall back to the CPU. This change enhances performance, especially in scenarios requiring large k values, such as qwen4exp's sparse-attention indexer. The update ensures that operations are more efficient and scalable, providing a notable boost in processing speed without regressing any measured shapes.