b9775

ggml-org/llama.cppb9775Jun 23, 2026by github-actions[bot]same day as b9774

What changed since b9774

low risk

Server now checks draft context creation errors for better debugging.

New features

  • Server now validates draft context creation errors
  • Added error checking for draft context in server component

Improvements

  • Improved error reporting and debugging for draft contexts
  • Enhanced server error handling for draft context failures

Upgrade notes

No configuration changes or migration steps are required.

Analyzed Oct 17, 2026

Upgrading?

Release notes summary

The server component now includes a check for draft context creation errors to improve error reporting and debugging.

Key Highlights

  • Check draft context creation error in server
  • macOS/iOS binaries
  • Linux binaries
  • Windows binaries

Release Notes (excerpt)

<details open> server : check draft context creation error (#24922) </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) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) **Android:** - Android arm64 (CPU) **Windows:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories