b10240

ggml-org/llama.cppb10240Aug 3, 2026by github-actions[bot]same day as b10238

What changed since b10238

low risk

b10238 added MTP support for Qwen3-Next; b10240 added a notice for a future server port change.

New features

  • Added a notice regarding the upcoming server port change (8080 -> 9931)

Improvements

  • Refactored `opt_num_mtp_layers` and comments in b10238
  • Added link to the related pull request in b10240

Bug fixes

  • Fixed Python type-checking issues in b10238

Upgrade notes

b10238 introduces MTP support for Qwen3-Next. b10240 adds a notice about a future default server port change from 8080 to 9931; no action is required yet.

Analyzed Oct 16, 2026

Upgrading?

Release notes summary

Added a notice regarding an upcoming change to the server's default port from 8080 to 9931.

Key Highlights

  • Added notice for upcoming default port change (8080 -> 9931)
  • Added link to the related pull request

Release Notes (excerpt)

<details open> server: add notice for upcoming default port change 8080 --> 9931 (#26508) * server: add notice for upcoming default port change 8080 --> 6631 * add link to PR * correct to 9931 </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories