Models & Labs
Cross-Origin Storage API in Transformers.js
Hugging Face Bloghigh confidence
Why it matters
- →The Cross-Origin Storage API could drastically reduce redundant data downloads across web apps.
- →It introduces a new way to manage resources using cryptographic hashes, enhancing efficiency.
- →This proposal could lead to significant bandwidth and storage savings for developers.
Hugging Face is exploring the Cross-Origin Storage API in Transformers.js to address redundant downloads of AI models and Wasm files across different web app origins. This API uses cryptographic hashes to identify resources, allowing them to be shared across origins without duplicating downloads. Currently, browser caches are isolated by origin, leading to unnecessary bandwidth and storage use. While the API is not yet implemented in browsers, developers can test it using a polyfill extension, potentially paving the way for more efficient web app resource management.
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.