DEV Community

# nvidia

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
FlashAttention CUDA Speedup, RTX 5090 LLM Performance, & NVIDIA Blackwell GPU Launch
soytuber profile
soy

FlashAttention CUDA Speedup, RTX 5090 LLM Performance, & NVIDIA Blackwell GPU Launch

#gpu #nvidia #hardware
Comments
3 min read
Stop Guessing Your Next GPU: I Built a GPU Upgrade Value Calculator
logarithmicspirals profile

Stop Guessing Your Next GPU: I Built a GPU Upgrade Value Calculator

#gpu #amd #nvidia #performance
2
Comments
4 min read
RTX 4090 Cooling, LLM KV Cache Quantization, & Deepseek V4 Flash Models
soytuber profile
soy

RTX 4090 Cooling, LLM KV Cache Quantization, & Deepseek V4 Flash Models

#gpu #nvidia #hardware
Comments
3 min read
Photonic NPU Chips: The Light-Based Tech That Could Make NVIDIA GPUs Obsolete [2026]
kunal_d6a8fea2309e1571ee7 profile

Photonic NPU Chips: The Light-Based Tech That Could Make NVIDIA GPUs Obsolete [2026]

#photonicnpu #nvidia #aihardware #semiconductors
Comments
8 min read
Deepseek TileKernels, RTX 3090 LLM Benchmarks & Nvidia Inference Dashboard
soytuber profile
soy

Deepseek TileKernels, RTX 3090 LLM Benchmarks & Nvidia Inference Dashboard

#gpu #nvidia #hardware
Comments
3 min read
Google TPU 8 vs Nvidia: 8t and 8i Specs Explained
monkfromearth profile

Google TPU 8 vs Nvidia: 8t and 8i Specs Explained

#ai #infrastructure #google #nvidia
Comments
9 min read
CUDA Triton Optimization, RTX Remix VFX Update, and VSR Benchmarks
soytuber profile
soy

CUDA Triton Optimization, RTX Remix VFX Update, and VSR Benchmarks

#gpu #nvidia #hardware
Comments
4 min read
Tesla P40 in a Homelab: 24GB of Inference on a Budget
futhgar profile

Tesla P40 in a Homelab: 24GB of Inference on a Budget

#teslap40 #nvidia #proxmox #ollama
Comments 2
6 min read
NVIDIA Pushes GPU Tech: DLSS 4.5, Streamline 2.11.1 SDKs & RTX Remix Updates
soytuber profile
soy

NVIDIA Pushes GPU Tech: DLSS 4.5, Streamline 2.11.1 SDKs & RTX Remix Updates

#gpu #nvidia #hardware
Comments
3 min read
When Tokens Cost 12 Cents Per Million, The Bottleneck Isn't Cost. It's Control.
pat9000 profile

When Tokens Cost 12 Cents Per Million, The Bottleneck Isn't Cost. It's Control.

#aiagents #agentguard #nvidia #blackwell
Comments
4 min read
Local LLM on NVIDIA GPU vs Cloud API: A Real Cost Analysis
ppcvote profile

Local LLM on NVIDIA GPU vs Cloud API: A Real Cost Analysis

#nvidia #gpu #localllm #cloudapi
Comments
5 min read
NVIDIA Vera Rubin 192GB SOCAMM2 Memory, SASS Reverse Engineering, & CUDA Kernel Dev
soytuber profile
soy

NVIDIA Vera Rubin 192GB SOCAMM2 Memory, SASS Reverse Engineering, & CUDA Kernel Dev

#gpu #nvidia #hardware
Comments
3 min read
Personal token factory: OpenClaw in AWS but Nvidia GB10 at home
ppabis profile

Personal token factory: OpenClaw in AWS but Nvidia GB10 at home

#openclaw #nvidia #vpn #aws
Comments
18 min read
CUDA Kernels in Python, GDDR7 Memory Breakthrough, and Radeon RX 9060 XT Launch
soytuber profile
soy

CUDA Kernels in Python, GDDR7 Memory Breakthrough, and Radeon RX 9060 XT Launch

#gpu #nvidia #hardware
Comments
4 min read
Diffusion Language Models: How NVIDIA Nemotron-Labs Diffusion Shatters the Autoregressive Speed Ceiling
monuminu profile

Diffusion Language Models: How NVIDIA Nemotron-Labs Diffusion Shatters the Autoregressive Speed Ceiling

#ai #llm #nvidia #machinelearning
Comments
18 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.