b9902

ggml-org/llama.cppb9902Jul 7, 2026by github-actions[bot]same day as b9901

What changed since b9901

low risk

b9902 adds SYCL backend support for cross_entropy_loss and its backward pass, with no other changes.

New features

  • SYCL backend now implements the cross_entropy_loss operation.
  • SYCL backend now implements cross_entropy_loss_back for gradient computation.

Upgrade notes

This is an additive change scoped to the SYCL backend, so no config or API changes are required. Users on other backends (CUDA, Metal, Vulkan, CPU) see no behavioral difference. SYCL users running training or loss-based workloads can now offload these ops to the GPU.

Analyzed Oct 31, 2026

Upgrading?

Release notes summary

Adds support for SYCL operations cross_entropy_loss and cross_entropy_loss_back, expanding SYCL functionality for machine learning tasks.

Key Highlights

  • SYCL cross_entropy_loss support
  • Backward pass implementation for cross entropy loss
  • Expanded SYCL functionality for ML operations

Release Notes (excerpt)

<details open> [SYCL] support OP cross_entropy_loss, cross_entropy_loss_back (#25236) * support OP cross_entropy_loss, cross_entropy_loss_back * correct format issue </details> **macOS/iOS:** - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) - iOS XCFramework **Linux:** - Ubuntu x64 (CPU) - Ubuntu arm64 (CPU) - Ubuntu s390x (CPU) - Ubuntu x64 (Vulkan) - Ubuntu arm64 (Vulkan) - Ubuntu x64 (ROCm 7.2) - Ubuntu x64 (OpenVINO)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories