Anthropic released Claude Code v2.1.316, focusing on enterprise governance and stability fixes. Key additions include CLAUDE_CODE_DISABLE_ULTRATHINK to turn off deep reasoning keywords, CLAUDE_CODE_SUBAGENT_EFFORT for controlling autonomous agent resource usage, and pooled group budgets for shared spending limits via the gateway API. The update resolves several bugs involving hanging shell processes, corrupted bash aliases, and network request timeouts on Windows and macOS.
Read originalEarlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
Matt Wolfe · July 29, 2026 · Same story
Lev Selector · July 31, 2026 · Same story
Wes Roth · September 1, 2026 · Same story
The Verge AI · September 17, 2026 · Same story
Duncan Rogoff · September 23, 2026 · Same story
Claude Code Releases · October 2, 2026 · Same story
TechCrunch AI · October 6, 2026 · Same story
Claude Code Releases · October 10, 2026 · Same story
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
This release quietly expands llama.cpp's hardware support to include Qualcomm Snapdragon devices with CPU, Adreno GPU, and Hexagon NPU acceleration. It also updates ROCm to version 10.0 for both Linux and Windows, keeping AMD users in step with the latest driver stack. CUDA builds now default to 13.4 libraries alongside 12.x options, reflecting the industry's gradual shift toward newer NVIDIA toolkits. While no new model architectures are introduced, the binary matrix grows significantly, ensuring local inference remains viable on a wider array of edge and server hardware.