Best of GPUJanuary 2026

  1. 1
    Article
    Avatar of phoronixPhoronix·19w

    Burn 0.20 Released: Rust-Based Deep Learning With Speedy Perf Across CPUs & GPUs

    Burn 0.20 introduces CubeK, a high-performance multi-platform kernel system built on CubeCL that enables unified CPU and GPU execution across NVIDIA CUDA, AMD ROCm, Apple Metal, WebGPU, and Vulkan. The release aims to deliver peak performance on diverse hardware without maintaining fragmented codebases, with benchmarks showing significantly lower execution times compared to LibTorch and ndarray. The update also includes a complete overhaul of the ONNX import system and various stability improvements.

  2. 2
    Article
    Avatar of modal_labsModal·20w

    Keeping 20,000 GPUs healthy

    Modal manages over 20,000 GPUs across AWS, GCP, Azure, and OCI, encountering significant reliability and performance differences between cloud providers. Their GPU health system includes instance type benchmarking and selection, machine image preparation with automated testing, boot-time validation, and continuous passive monitoring (via DCGM and dmesg) plus weekly active healthchecks (DCGM diag, GPUBurn, NCCL tests). Key findings: Cloud providers vary dramatically in H100 performance (up to 50% differences), temperature management (some reaching 94°C), and ECC error rates. GPUs account for 58.7% of training failures in Meta's LLaMA 3 development, compared to just 0.5% for CPUs, highlighting the reliability gap.

  3. 3
    Article
    Avatar of chromeChrome Developers·20w

    What's New in WebGPU (Chrome 144)

    Chrome 144 introduces two new WGSL language extensions: subgroup_id for accessing subgroup identifiers within workgroups, and uniform_buffer_standard_layout for simplified memory layout alignment between uniform and storage buffers. WebGPU is rolling out on Linux starting with Intel Gen12+ GPUs. Performance improvements include up to 2X faster writeBuffer() and writeTexture() operations. The Android GPU team released the first alpha of Kotlin bindings for WebGPU through Jetpack's androidx.webgpu package.