Coding Tools
llama.cpp adds OCP FP8 E4M3 support
llama.cpp Releaseshigh confidence
Why it matters
- →Enables efficient local inference for new models using OCP FP8 E4M3 quantization.
- →Fixes critical conversion bugs for fused QKV projections and shared scales.
- →Adds fast CPU kernels, reducing reliance on GPU acceleration for FP8 workloads.
The llama.cpp project has merged support for OCP FP8 E4M3 quantization, enabling efficient inference for models using this specific precision format. Key technical additions include fast CPU kernels for F8_E4M3 and robust conversion tools that handle complex scenarios like fused QKV projections and shared scales found in models such as Qwen3-Next. The update also resolves previous bugs where FP8 tensors were incorrectly downgraded to NVFP4 during conversion. This release expands the range of compatible model architectures available for local deployment on standard hardware.
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 fixes 4D tensor quantization for MoE models
llama.cpp Releases · October 26, 2026 · Same story
What happened next
- 2llama.cpp adds OpenCL iq3 quantization support
llama.cpp Releases · November 1, 2026 · Same story
Follow this story
Open the full story →Liquid AI releases LFM3 multimodal models
3 developments
- Oct 27 · Hugging Face Blog
Liquid AI releases LFM3 multimodal models - Oct 28 · llama.cpp Releases
llama.cpp adds LiquidAI LFM3 model support↳ llama.cpp adds support for LiquidAI LFM3 models to enable local inference on Apple Silicon and AMD ROCm GPUs. - Oct 30 · llama.cpp Releases
llama.cpp adds OCP FP8 E4M3 support (This article)↳ llama.cpp adds OCP FP8 E4M3 quantization support with fast CPU kernels and fixes for fused QKV projections.
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
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.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
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.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12024 adds Snapdragon and ROCm 10
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.
llama.cpp Releases
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
© The Verge AICoding Toolscoding
DIY Muse Gadget proves Meta's hardware is just a dev kit
Meta’s Muse Charm isn’t a finished product; it’s an invitation to hack. A non-coder used Claude Code to transform a $50 Waveshare ESP32-S3 dev board into a fully functional AI companion, adding ElevenLabs voice synthesis, custom Tamagotchi-style minigames, and remote camera controls that Meta’s official firmware lacks. This reveals a critical truth: the value of Meta’s new hardware ecosystem lies not in its out-of-the-box utility, but in its open-source API allowing anyone to rewrite the experience. The gap between Meta’s polished demo and the actual user reality is bridged entirely by third-party AI coding tools.
The Verge AI
© The AI Daily BriefCoding Toolswriting
Granola launches free dictation feature
Granola has released a new free dictation tool for users.
The AI Daily Brief