From Dev.to Community
Tech Articles
Curated developer articles, tutorials, and guides — auto-updated hourly
xbillSep 16, 2026 • 6 min read
A 4 GB Laptop GPU Beats a 12-Core CPU by 4.3x on Gemma 4
Serving Gemma 4 E2B q4_0 through llama.cpp on one laptop, twice: CPU-only and on a 2021-era 4 GB GTX...
#machinelearning#gpu#benchmarking#python
15 7
Aleksei RomanovSep 21, 2026 • 9 min read
High-Throughput LLM Inference & Training: A Deep Dive into vLLM
Editor's Note: Originally published on the g factor engineering blog. All benchmarks and telemetry.....
#ai#machinelearning#python#gpu
1 1
Sumukh ShenoySep 22, 2026 • 3 min read
Why GPU Availability Is Still the Biggest Bottleneck in ML Infra
If you've ever had a training job ready to go and then sat there refreshing your cloud console...
#machinelearning#infrastructure#gpu#devops
1 1
Yehor CherednichenkoSep 17, 2026 • 6 min read
Half of my FP8 convolutions were silently running in f32 – a one-line XLA fix
A stray return made XLA:GPU skip FP8 rewriting for most of a module I'm training a...
#machinelearning#performance#compilers#gpu
2 1
Sho Tanaka (tsho)Sep 16, 2026 • 10 min read
DeepSpeed ZeRO vs PyTorch FSDP2, Measured: 1.8x on NVLink, Barely Finishing on PCIe (Plus How to Actually Get GPUs on GKE)
Introduction DeepSpeed ZeRO and PyTorch FSDP are the two standard answers to "my model...
#machinelearning#pytorch#deepspeed#gpu
0 0
Fyodor SerzhenkoSep 18, 2026 • 13 min read
Same nvJPEG2000, different numbers: timer boundaries and frames in flight
What NVIDIA's own JPEG2000 samples leave out of the timer, and how feeding several frames at once sp...
#cuda#gpu#performance#cpp
0 0
Mr Say NothingSep 16, 2026 • 6 min read
Ollama Not Using GPU? Fix It on Linux, Windows and WSL
Ollama ignoring your GPU and falling back to CPU? The five real causes — drivers, VRAM, pinned backe...
#ollama#gpu#linux#windows
0 0
ComradePenguinSep 18, 2026 • 10 min read
Exploring Result Visibility of Fixed-Latency Instructions on the SM120 Architecture
Huerta et al., in Dissecting and Modeling the Architecture of Modern GPU Cores, propose that modern....
#cuda#nvidia#gpu
1 0
ram.mehta.1899@gmail.comSep 22, 2026 • 1 min read
Evaluating Multi-Node LLM Orchestrators: Exo, GPUStack, and LocalAI
A pragmatic teardown of self-hosted multi-node LLM orchestrators comparing zero-config P2P, supervis...
#llm#platformengineering#infrastructure#gpu
0 0
VoltageGPUSep 17, 2026 • 4 min read
I asked whether my own API could get a customer both attestation proofs with nothing but a key. It could not. Here is what was missing.
I sell Intel TDX virtual machines with a NVIDIA GPU passed through, and the whole pitch is "you...
#security#cloud#gpu#python
1 0
Anupam PatilSep 18, 2026 • 4 min read
Bend: A Revolutionary Programming Language to Prevent AI Mistakes on CPUs and GPUs
Bend is transforming the world of parallel programming. Its groundbreaking ability to optimize for.....
#bend#aiprogramming#cpu#gpu
0 0
AI ExploreSep 22, 2026 • 7 min read
DuckDB on the Apple Silicon GPU: Plain SQL, 19 of 22 TPC-H Queries on the Mac's Own GPU, and a Rule That Says Never Slower
Run DuckDB on your Mac's GPU. gpudb 0.7 puts plain SQL on Apple silicon Metal and NVIDIA CUDA, only ...
#duckdb#gpu#sql#database
0 0
Viktor LogvinovSep 22, 2026 • 12 min read
Go Developers Sought to Enhance Zerfoo: A Unified ML Framework in Go for Model and App Deployment
Introduction Zerfoo, a Go-based machine learning (ML) framework, emerged from a...
#go#machinelearning#framework#gpu
0 0
Elena BurtsevaSep 19, 2026 • 11 min read
Choosing Between GPU Upgrade for UnRaid or Mac Mini for Efficient Large Language Model Performance
Introduction Deploying a Large Language Model (LLM) efficiently demands hardware capable...
#llm#gpu#macmini#unraid
0 0
Damian DixonSep 20, 2026 • 3 min read
The Multi-Cloud Paradigm Shift: Why No Single GPU Provider Can Carry Serious AI Workloads Anymore
16 of 18 real GPU jobs required automatic failover mid-run. Zero were dropped. That's not a number....
#ai#cloud#gpu#infrastructure
5 0
Reno LuSep 17, 2026 • 3 min read
FreeToken uses bandwidth-adaptive CPU-GPU co-execution on your desktop
FreeToken is a MoE serving engine for consumer hardware with CPU-GPU co-execution, expert caching, a...
#moe#localllm#inference#gpu
0 0
GitHubOpenSourceSep 18, 2026 • 3 min read
GPUMesh: Unleash Your GPUs with a Private, Peer-to-Peer Compute Network!
Quick Summary: 📝 GPUMesh enables secure, peer-to-peer sharing of Docker GPU jobs among...
#gpu#distributed#peertopeer#docker
0 0
Johnny is piggySep 18, 2026 • 20 min read
GPU-Accelerated Optimization Algorithms: A Complete Survey and Selection Guide (2026)
From NVIDIA cuOpt's 5000x LP speedups to the Muon optimizer — a full-domain map of GPU-accelerated o...
#optimization#gpu#machinelearning#programming
0 0
vikas sharmaSep 18, 2026 • 2 min read
Cloud GPU Computing for AI Development and Scalable Workloads
Computing requirements can change quickly when developers and organizations work with artificial...
#cloudcomputing#gpucomputing#cloud#gpu
1 0
Cyfuture AISep 18, 2026 • 9 min read
Rent NVIDIA B300 GPU: High-Performance AI Computing Without Buying Hardware
Artificial intelligence is advancing rapidly, and businesses need powerful computing infrastructure....
#ai#b300#gpu#webdev
0 0
CTCserversSep 17, 2026 • 1 min read
Supercharge Your Data Science Workflows with NVIDIA RAPIDS & GPU Servers
Are you tired of waiting hours or even days for Pandas and Scikit-Learn to process massive...
#nvidia#rapids#gpu#datascience
0 0
Cyfuture AISep 22, 2026 • 8 min read
Rent NVIDIA RTX PRO 6000 Server for Enterprise AI Infrastructure
Enterprise AI workloads are becoming increasingly demanding. Businesses are deploying large...
#ai#rtx600#gpu#webdev
0 0
![How to Serve a Local LLM to Multiple Users [2026]](https://media2.dev.to/dynamic/image/width=1200,height=627,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fmd7a9fvgiwl3zyjrffou.png)
KunalSep 16, 2026 • 12 min read
How to Serve a Local LLM to Multiple Users [2026]
If your local LLM server “works” but falls apart at 30–50 concurrent chats, this guide shows the rea...
#vllm#sglang#tgi#gpu
0 0
Claw Tech DailySep 17, 2026 • 4 min read
RTX 5090 at $9,000 Is Not a Typo — and the RTX 6000 Rumor Isn't Helping
I've been staring at GPU price trackers long enough to stop being surprised, but this week...
#hardware#nvidia#gpu#tech
0 0