b10176

ggml-org/llama.cppb10176Jul 29, 2026by github-actions[bot]same day as b10175

What changed since b10175

low risk

b10176 adds an RPC `tensor_memset` command for remotely setting tensor memory, on top of b10175's AMD mmq tuning.

New features

  • New RPC command `tensor_memset` allows setting tensor memory values on remote RPC backends.

Improvements

  • Extends the RPC protocol surface with a memory-initialization primitive, complementing existing tensor transfer operations.

Upgrade notes

This is a single-commit increment over b10175; the only delta is the new RPC command, so no config or model changes are required. RPC clients and servers should be upgraded together if you intend to use `tensor_memset`, since older servers won't recognize the command. The RDNA3/RDNA3.5 mmq tuning from b10175 is unchanged.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Added a new RPC command `tensor_memset` to enable setting tensor memory values remotely.

Key Highlights

  • Added tensor_memset RPC command

Release Notes (excerpt)

<details open> RPC: add tensor_memset (#25912) </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) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) **Android:** - Android arm64 (CPU)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories