Models & Labs
llama.cpp Adds WebGPU Depthwise Conv2D Kernel
llama.cpp Releaseshigh confidence
Why it matters
- →Expands llama.cpp's capabilities with WebGPU, enhancing performance for AI tasks.
- →Provides developers with more flexibility in choosing computational backends.
- →Strengthens llama.cpp's position as a versatile AI framework across platforms.
Llama.cpp has released an update adding a depthwise convolutional 2D kernel to its WebGPU backend. This kernel, originally from the Vulkan backend, enhances the framework's computational capabilities. The update also includes minor code cleanups and updates to supported operations tables. This development is significant for developers using WebGPU, as it expands the framework's versatility and performance in handling AI tasks.
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 b9684 Release Adds 3D Convolution
llama.cpp Releases · June 18, 2026 · Same story
What happened next
- 2llama.cpp adds WebGPU Q2_0 support
llama.cpp Releases · October 22, 2026 · Same story
Follow this story
Open the full 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.
More in Models & Labs
© GitHub ChangelogModels & Labscoding
Gemini 4 Hydrogen arrives in GitHub Copilot
Google’s latest Flash model is now generally available in GitHub Copilot, targeting agentic coding and multistep workflows. It offers improved instruction following over Gemini 3.8 Flash and is billed at provider list pricing under usage-based billing. The rollout is gradual across Visual Studio Code, JetBrains IDEs, and other platforms. Administrators can manage access through model policies in Copilot settings.
GitHub Changelog
© TechCrunch AIModels & Labs
