🐧 PenguinPulse

Linux Graphics & Gaming News

Articles tagged: cuda

← Back to all articles

PyTorch 2.10 Released with AMD ROCm and Intel GPU Improvements

PyTorch 2.10 was released today, January 22, 2026, as the latest feature update to the deep learning library. This new release continues to improve support for Intel GPUs and the AMD ROCm compute stac...

Read more →

Ollama 0.14.1 Introduces Experimental Image Generation Models for Linux (CUDA)

Ollama v0.14.1 was released today, January 18, 2026, bringing experimental support for image generation models. This new functionality is available for Linux systems configured with CUDA-compatible GP...

Read more →

ZLUDA Adds Full Llama.cpp Support, Improves Windows Handling for CUDA on Non-NVIDIA GPUs

The open-source ZLUDA project announced its progress from the fourth quarter of 2025 today, January 14, 2026. ZLUDA, which aims to enable unmodified CUDA applications to run on non-NVIDIA GPUs, now bo...

Read more →

NVIDIA Open-Sources CUDA Tile Intermediate Representation

NVIDIA announced yesterday that its CUDA Tile intermediate representation (IR) is now open-source software. The company dropped the proprietary license for the IR, which previously restricted its use ...

Read more →

Ollama v0.13.2-rc2 Boosts Vision Model AI Performance, Fixes Multi-GPU CUDA

Ollama has recently released version 0.13.2-rc2, bringing several updates focused on AI model performance and GPU compatibility. A significant change is the default enablement of flash attention for v...

Read more →

NVIDIA Releases CUDA 13.1 With New CUDA Tile Programming Model

NVIDIA today released CUDA 13.1, which the company claims is "the largest and most comprehensive update to the CUDA platform since it was invented two decades ago." The most notable addition in this r...

Read more →

Ollama v0.13.1-rc0 Improves CUDA VRAM Discovery, Adds Cogito-v2.1 Tool Calling

Ollama recently released version 0.13.1-rc0, introducing several updates for local large language model development. This release addresses specific issues with CUDA VRAM discovery, which should lead ...

Read more →