b9936
ggml-org/llama.cppb9936Jul 9, 2026by github-actions[bot]same day as b9935
What changed since b9935
Server fix makes prompt batch splitting honor the minimum step size; no other changes between b9935 and b9936.
Bug fixes
- Server-side prompt batch splitting now respects the configured minimum step size, avoiding undersized splits.
Upgrade notes
This is a single-commit server fix with no config or API changes; a straight binary swap is sufficient. Users running the server with small batch or step settings should upgrade to get correct batch splitting behavior.
Analyzed Oct 24, 2026
Upgrading?
Release notes summary
Server-side fix ensuring prompt batch splitting respects the minimum step size.
Key Highlights
- Server now respects min-step when splitting prompt batches
Release Notes (excerpt)
<details open> server : respect min-step when splitting prompt batches (#25420) </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)…
Published by ggml-org on GitHub.
Read the full release notesRelated Repositories
:electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS
Godot Engine – Multi-platform 2D and 3D game engine
ClickHouse® is a real-time analytics database management system
Self-hosted game stream host for Moonlight.
DuckDB is a high-performance analytical database system