b9686

ggml-org/llama.cppb9686Jun 17, 2026by github-actions[bot]same day as b9685

What changed since b9685

low risk

Single-commit patch fixing an Eagle3 speculative decoding segfault on long prompts.

Bug fixes

  • Resolved a segmentation fault triggered by long prompts when using the Eagle3 speculative decoding model.

Upgrade notes

This is a one-commit patch on top of b9685; no config or API changes are involved. Users running Eagle3 speculative decoding with long prompts should upgrade to avoid crashes. Everyone else can treat it as a routine housekeeping bump.

Analyzed Oct 31, 2026

Upgrading?

Release notes summary

Fixes a segmentation fault that occurred when processing long prompts with the Eagle3 model specification.

Key Highlights

  • Segfault error fix for Eagle3
  • Long prompt stability improvement

New Features

  • Eagle3 long prompt handling fix

Release Notes (excerpt)

<details open> spec: fix segfault error on long prompts for eagle3 (#24707) </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