Coding Tools
llama.cpp b12407 optimizes LFM3 on Metal
llama.cpp Releaseshigh confidence
Why it matters
- →Optimizes LFM3 inference specifically for Apple Silicon Metal backends.
- →Enables norm fusion by reordering residual tensor operations.
- →Improves local performance without altering model weights or logic.
llama.cpp version b12407 introduces a workaround for Metal fusion issues affecting the LFM3 model architecture. The update reorders tensors in residual additions to enable norm fusion, optimizing memory usage on Apple Silicon hardware. This change addresses specific performance constraints identified during testing of the LFM3 variant. The release includes updated test baselines to verify the stability of this optimization.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1llama.cpp b10232 release enhances Metal support
llama.cpp Releases · August 3, 2026 · Same story
- 2llama.cpp b11059 optimizes Metal FWHT for Apple Silicon
llama.cpp Releases · September 20, 2026 · Same story
- 3vLLM v0.34.0rc0 adds Gemma and StableLM support
vLLM Releases · November 11, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12398 optimizes Vulkan Flash Attention for AMD
This release targets the persistent performance gap on AMD hardware by optimizing Vulkan Flash Attention specifically for RDNA3 and RDNA4 architectures. The changes include reducing shared memory usage through buffer reuse and fixing critical stability issues like NVIDIA hangs and sparse FA underflow bugs. While there are no new model architectures, these low-level shader optimizations directly translate to faster inference speeds for local users on modern AMD GPUs. It is a quiet but necessary engineering update that tightens the ecosystem for non-NVIDIA accelerators.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12399 adds ROCm 10 and CUDA 13 builds
This release quietly extends llama.cpp’s hardware support to the latest NVIDIA and AMD stacks. By shipping binaries for CUDA 13.5 and ROCm 10.0, it ensures users on cutting-edge GPUs don't have to compile from source to get performance gains. The Vulkan build also fixes header inclusion issues that previously broke compilation on some Linux distributions. It’s a maintenance update rather than a feature leap, but it keeps the local inference runtime compatible with the fastest consumer and datacenter hardware available today.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12400 release with CUDA 13 and ROCm 10
This is a routine maintenance release for llama.cpp that quietly extends hardware support to the latest NVIDIA and AMD stacks. By adding CUDA 13.5 and ROCm 10.0 binaries, it ensures local inference remains viable on cutting-edge GPUs without waiting for community forks. The build also includes OpenVINO and SYCL variants, reinforcing its role as the universal runtime for diverse accelerators. While no new model architectures are introduced, this update keeps the toolchain compatible with modern driver ecosystems.
llama.cpp Releases
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.325 patches security and MCP stability
This release prioritizes stability over new features, addressing a critical zstd decompression vulnerability that could have exposed response data. Beyond security, it significantly hardens the reliability of Model Context Protocol (MCP) integrations, fixing persistent connection drops and authentication loops that plagued background tasks. The update also resolves context compaction failures on third-party gateways, ensuring sessions no longer crash when hitting token limits. For developers relying on Claude Code for complex workflows, this patch removes several friction points that previously interrupted automated coding sessions.
Claude Code Releases
© GitHub ChangelogCoding Toolscoding
GitHub Copilot Deprecates Claude Haiku 4.5 in Dec 2026
GitHub is quietly removing Claude Haiku 4.5 from its entire Copilot ecosystem by December 2026, a move that forces enterprise and business users to migrate away from Anthropic’s fastest model. While individual annual subscribers retain access, the deprecation signals a strategic shift in GitHub’s default model stack, likely prioritizing higher-margin or more integrated options like GPT-4o or newer Claude variants. This isn't just a sunset notice; it's a mandate for workflow updates, requiring administrators to actively manage model policies rather than relying on passive defaults. The move highlights the fragility of relying on third-party models within closed IDE ecosystems, where access can be revoked unilaterally. Developers must now audit their settings to ensure compliance with new default stacks. This transition marks a clear boundary between individual flexibility and enterprise control in AI tooling.
GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub Copilot app supports Enterprise Server
The GitHub Copilot desktop app finally reaches parity with the web interface for enterprise users. Version 1.2.0 makes GitHub Enterprise Server support generally available, allowing developers to connect their GHES accounts directly within the IDE-like environment. This closes a significant gap for organizations that cannot or will not use GitHub.com, enabling remote repository and pull request workflows without leaving the app. While cloud sessions remain unavailable for these instances, local inference on enterprise code is now fully integrated.
GitHub Changelog