b10037

ggml-org/llama.cppb10037Jul 16, 2026by github-actions[bot]same day as b10036

What changed since b10036

low risk

Quantization now accepts manual tensor type overrides alongside the --pure flag.

New features

  • The quantize tool can combine manual tensor type specifications with the --pure flag instead of having them mutually exclusive.

Upgrade notes

No action required for typical inference users; only affects those running quantization with --pure. If you previously had to drop manual tensor overrides when using --pure, you can now keep both. Existing quantization scripts remain compatible.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Enhances the quantization process to support manual tensor types when using the `--pure` flag.

Key Highlights

  • Allow using manual tensor types with `--pure` flag
  • Quantization improvement

Release Notes (excerpt)

<details open> quant : allow using manual tensor types with --pure (#25716) </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