Xla
PulseAugur coverage of Xla — every cluster mentioning Xla across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Nova compiler unlocks deep learning performance with aggressive optimization
Researchers have developed Nova, an end-to-end Just-In-Time (JIT) compiler designed to optimize deep learning model performance by gaining granular control over hardware and memory. Nova achieves this by fusing operatio…
-
MoE models suffer silent token drops due to capacity factor
A Mixture-of-Experts (MoE) model's performance can degrade in production due to a hidden issue called the MoE capacity factor. This factor dictates a fixed-size buffer for each expert, and if too many tokens are routed …
-
JAXBench launches to optimize AI kernels on Google TPUs
A new benchmark suite called JAXBench has been developed to specifically address the optimization of AI kernel performance on Google Cloud TPUs. This suite includes 50 JAX workloads derived from prominent AI models like…
-
New CRAX benchmark accelerates safe reinforcement learning evaluations
Researchers have introduced CRAX, a new benchmark designed to accelerate the evaluation of safe reinforcement learning (RL) agents. Built using the MuJoCo XLA physics engine, CRAX offers up to a 100x speedup compared to…
-
Apple details its on-device and server foundation models for Apple Intelligence
Apple has detailed its new foundation language models powering Apple Intelligence, including a ~3 billion parameter on-device model and a larger server-based model. These models are designed for multilingual and multimo…
-
George Hotz's tiny corp unveils $15K AI computer and RISC-based tinygrad framework
George Hotz's company, tiny corp, has launched the tinybox, a $15,000 personal AI computer designed for local model training and inference. The tinybox boasts 738 FP16 TFLOPS and 144 GB of GPU RAM, capable of running a …