b10079

ggml-org/llama.cppb10079Jul 22, 2026by github-actions[bot]same day as b10078

What changed since b10078

low risk

b10079 is a single server-side fix for null llama_context handling, with no changes to the Vulkan work from b10078.

Improvements

  • Server request handling is more robust when the context is unavailable, reducing crash exposure.

Bug fixes

  • Server now correctly handles a null llama_context pointer instead of risking a crash during request processing.

Upgrade notes

This is a narrow patch on top of b10078, so no config or API changes are required. Upgrading is only worthwhile if you run llama-server and want the added null-context safety; the Vulkan queue refactor from b10078 is unchanged.

Analyzed Oct 27, 2026

Upgrading?

Release notes summary

Fixes a bug in the server component where it failed to properly handle a null llama_context pointer, preventing potential crashes during request processing.

Key Highlights

  • Server null pointer fix for llama_context
  • Prevents crashes on invalid requests

New Features

  • Server stability improvement

Release Notes (excerpt)

<details open> server : properly handle null llama_context (#25868) Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com> </details> **Website:** - <https://llama.app> **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