Coding Tools
llama.cpp b11214 boosts AMD CDNA large batch performance
llama.cpp Releaseshigh confidence
Why it matters
- →Enables fattn-mma kernel for dkq > 256 on AMD CDNA, improving large batch throughput.
- →Updates CI to handle large MFMA kernels better, ensuring stability for high-performance builds.
- →Maintains broad platform support including CUDA 13 and ROCm 10.0 binaries.
llama.cpp has released version b11214, focusing on performance optimizations for AMD CDNA architecture. The key change enables the fattn-mma kernel for cases where dkq exceeds 256, improving efficiency for large batch sizes. The release also updates CI checks to ignore spills for very large MFMA kernels. Standard builds for CUDA 12/13, ROCm 10.0, and various CPU platforms remain available.
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 b10970 Release Expands Platform Support
llama.cpp Releases · September 15, 2026 · Same story
- 2llama.cpp b11046 adds OpenCL flash attention
llama.cpp Releases · September 19, 2026 · Same story
Follow this story
Open the full story →llama.cpp adds RDNA3.5 GPU support
2 developments
- Sep 16 · llama.cpp Releases
llama.cpp adds RDNA3.5 GPU support - Sep 28 · llama.cpp Releases
llama.cpp b11214 boosts AMD CDNA large batch performance (This article)↳ llama.cpp b11214 enables fattn-mma kernel for CDNA large batch performance
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b11213 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing first-class ROCm 10.0 support to both Linux and Windows. AMD GPU users no longer need workarounds for modern hardware, closing a long-standing parity gap with NVIDIA's CUDA ecosystem. Equally notable is the new Linux arm64 build targeting Snapdragon chips, which unlocks local LLM inference on high-performance mobile SoCs via CPU, Adreno GPU, and Hexagon NPU acceleration. While KleidiAI on Apple Silicon has been disabled in this specific binary set, the broader platform coverage signals a strategic shift toward hardware agnosticism that benefits anyone running models outside of standard NVIDIA setups.
llama.cpp Releases
Coding Toolscoding
llama.cpp b11215 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing first-class ROCm 10.0 support to both Linux and Windows. AMD GPU users no longer need workarounds, effectively closing a long-standing parity gap with NVIDIA's CUDA ecosystem. Equally notable is the new Snapdragon binary for Linux, which unlocks local AI on ARM-based laptops using Adreno GPUs and Hexagon NPUs. While KleidiAI on macOS has been disabled in this build, the expansion to AMD and Qualcomm hardware makes this one of the most significant platform broadening efforts yet.
llama.cpp Releases
Coding Toolscoding
llama.cpp adds wide SYCL FWHT kernels for Intel GPUs
Intel GPU users running llama.cpp finally get O(n log n) performance for large Hadamard transforms instead of falling back to slow dense matrix multiplication. This PR extends the Fast Walsh-Hadamard Transform kernel to handle block widths up to 8192, a critical optimization for certain quantization and attention mechanisms on SYCL hardware. The implementation uses work-group local memory to shuffle data efficiently, avoiding the quadratic cost that previously bottlenecked these operations. While it doesn't touch CUDA or ROCm, it significantly closes the performance gap for Intel Arc and Data Center GPU users who were left behind by previous narrow-kernel limits.
llama.cpp Releases
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.282 patches critical session and UX bugs
This release stabilizes Claude Code by fixing a cascade of session-breaking errors that previously caused silent data loss or API drops. The most significant fix addresses resumed conversations re-sending messages in altered forms, which was corrupting reasoning traces and breaking extended thinking workflows. It also resolves persistent login refresh loops and managed setting parsing failures that plagued enterprise deployments. While the changelog is dense with UI tweaks like scrollbar fixes and vim mode corrections, the core value lies in restoring reliability for long-running agent sessions.
Claude Code Releases
Coding Toolscoding
Claude Code v2.1.283: Gateway hints and plugin fixes
This release quietly solves a major pain point for enterprise AI workflows by adding gateway hint headers, allowing LLM gateways to correctly group requests per user prompt instead of treating them as isolated events. The new managed settings for availableModelsMatch and deniedModels give organizations precise control over model access, blocking specific versions even when broader allowances exist. Beyond governance, the update stabilizes the plugin ecosystem with rigorous validation checks that prevent silent failures from broken or misconfigured extensions. These changes shift Claude Code from a developer tool to a manageable enterprise component.
Claude Code Releases
© Matt WolfeCoding Toolsagents
OpenAI Introduces GPT-Live and Agent API
OpenAI launches GPT-Live 1 and a new Agent API, enabling real-time voice interactions and autonomous agent development.
Matt Wolfe