Models & Labs
Hugging Face Migrates Repositories to Xet Storage
Hugging Face Bloghigh confidence
Why it matters
- →Xet storage offers more efficient data handling through content-defined chunking.
- →The migration demonstrates Hugging Face's commitment to improving AI development infrastructure.
- →This shift could significantly enhance collaboration and iteration on large datasets.
Hugging Face has migrated its first model and dataset repositories from LFS to Xet storage, marking a significant advancement in storage efficiency. The new system uses content-defined chunking to deduplicate data at the byte level, allowing for faster and more efficient uploads. This migration has already shifted 6% of the Hub's download traffic to Xet, validating its capability to handle large-scale data transfers. The transition is part of Hugging Face's ongoing efforts to improve collaboration and iteration for AI developers working with massive datasets.
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.