Install
CUDA & Compute
CUDA, creator workloads, AI frameworks, and encoder/decoder blocks.
- 17 Tracked terms
- Last 30 days Feed window
What this topic collects on
An article joins this feed when it matches these terms. Each one is also a search of its own.
Related topics
Latest in CUDA & Compute
NVIDIA Isaac ROS Accelerates ROS 2 Nodes with CUDA Backend
1+ day, 8+ hour ago (223+ words) Timothy Morano Sep 22, 2026 14:15 NVIDIA's Isaac ROS 5.0 introduces CUDA buffer backend for ROS 2, enabling GPU-optimized robotics workflows with minimal code changes. A key enabler of this technology is NVIDIA's AI-driven agent skill, migrate-node-to-rosidl-buffer. This tool guides developers through the migration of…...
A 4 GB Laptop GPU vs a 6-Core CPU on Gemma 4, Re-Measured in ABBA Order: 4.1x
10+ hour, 7+ min ago (1209+ words) This article provides a step by step guide to measuring a laptop GPU against the CPU in the same chassis for serving Gemma 4 E2B through llama.cpp, with both builds on a fresh Debian sid toolchain and the passes run in…...
Can vLLM Run GGUF? Yes — on GPU Only
10+ hour, 35+ min ago (357+ words) Two steps: install the plugin, then point vLLM at the model. GGUF support no longer ships inside core vLLM — the docs note it "has migrated to OOT vllm-gguf-plugin", so a plain pip install vllm is not enough: The --tokenizer flag…...
Gemma 4 on a Tesla T4, Part 2: The Minimum GCE VM and a Script to Drive It
1+ day, 9+ hour ago (1553+ words) Part 1 began with the GPU already working. This part begins with a Google Cloud project and nothing in it. The work splits in two. Everything before first boot is a single gcloud command whose choices are GPU choices: which zone…...
How to run Gemma 4 locally: a setup that survives
1+ day, 14+ hour ago (482+ words) Start with text, add GPU offload and vision carefully, then pin the command and runtime that keep Gemma 4…. Tagged with technology, gemma4, localllms, homelab....
AES-GCM vs AES-GCM-SIV: 48% Slower, Nonce-Safe [2026]
2+ day, 14+ hour ago (669+ words) Here is the side-by-side spec sheet, pulled from the governing standards documents rather than marketing copy. Sixteen rows, covering the cryptographic parameters, the standardization status, and the practical support you will actually hit when you go to implement either mode…...
Gemma 4 on a Tesla T4: QAT Weights Decode 1.79x Faster Than bf16
5+ day, 5+ hour ago (1298+ words) The GPU is already there. A T4 attached to a Compute Engine VM needs no queued resource, no instance launch and no image, so this rig has no provisioning tools at all. Everything it ships is about the software on the…...
Serving Gemma 4 on an AMD MI300X: What $1.99 an Hour Buys
6+ day, 5+ hour ago (1104+ words) The card is a DigitalOcean GPU droplet reached through AMD Developer Cloud (devcloud.amd.com) — same v2 API, same droplet ids, token from the My AMD Team account. Creating and destroying it are console actions, deliberately: both are dollar-per-hour decisions and…...
A Pedagogical Introduction to Porting a Conjugate Gradient Solver to CUDA
1+ week, 6+ hour ago (1676+ words) GPU programming tutorials often begin with isolated examples: vector addition, reductions, matrix multiplication, and memory coalescing. These are useful for learning individual CUDA concepts, but there is another question that quickly arises when working with real scientific software: How do…...
A 4 GB Laptop GPU Beats a 12-Core CPU by 4.3x on Gemma 4
1+ week, 7+ hour ago (736+ words) This article compares two ways of serving the same small language model on the same laptop: CPU-only, and on the 4 GB GTX 1650 Ti sitting in the same chassis. The payload is byte-identical on both arms and the command lines differ…...