Models & Labs
OpenAI unveils Jalapeño, its first custom AI chip
The Rundown AIhigh confidence
Why it matters
- →Jalapeño represents a strategic move for OpenAI to control its compute layer, reducing reliance on external suppliers like Nvidia.
- →The rapid development cycle of Jalapeño, aided by AI, sets a new benchmark for ASIC chip design efficiency.
- →Owning the hardware allows OpenAI to optimize performance and cost across its AI models and products.
OpenAI has announced Jalapeño, its first custom AI chip developed with Broadcom, marking a strategic shift towards owning its compute infrastructure. The chip, designed for inference, reportedly offers performance per watt that exceeds current industry standards. Developed in just nine months, Jalapeño showcases OpenAI's ability to rapidly innovate in hardware, with its own AI models playing a key role in the design process. This development could significantly reduce OpenAI's dependency on Nvidia, as the company aims to power 10 GW of compute with custom chips by 2029.
Read originalMore from The Rundown AI
More 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.