DEV Community

#nvidia

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
NVIDIA DGX Spark vs. Mac Studio M5 Ultra: Which One Should You Actually Buy to Run AI Locally?
egepakten profile

NVIDIA DGX Spark vs. Mac Studio M5 Ultra: Which One Should You Actually Buy to Run AI Locally?

#ai #nvidia #m5studio #localpc
Comments
10 min read
Custom Object Detection on Jetson Orin Nano
sampreeth profile

Custom Object Detection on Jetson Orin Nano

#nvidia #ai #machinelearning #ultralytics
3
Comments 2
3 min read
OpenAI Jalapeño puts NVIDIA's inference margins on the clock
congar97 profile

OpenAI Jalapeño puts NVIDIA's inference margins on the clock

#ai #nvidia #machinelearning #architecture
3
Comments 2
11 min read
Borrowed an H100 but couldn't draw a single frame — Why compute GPUs and rendering GPUs are different beasts
orca_forge profile

Borrowed an H100 but couldn't draw a single frame — Why compute GPUs and rendering GPUs are different beasts

#gpu #nvidia #webgl
Comments
6 min read
The Great Ubuntu Blackout: My 3-Hour Journey to Fix the Darkness
arundevs profile

The Great Ubuntu Blackout: My 3-Hour Journey to Fix the Darkness

#ubuntu #linux #nvidia #graphics
1
Comments 2
8 min read
Accelerating Physical AI Workloads with NVIDIA CUDA and TensorRT
vmodal_ai profile

Accelerating Physical AI Workloads with NVIDIA CUDA and TensorRT

#cuda #nvidia #ai #machinelearning
Comments
2 min read
Nvidia em 2024: Por que as buscas dispararam e geram dinheiro
leojulieta profile

Nvidia em 2024: Por que as buscas dispararam e geram dinheiro

#nvidia #ia #datacenter #portugues
3
Comments 1
5 min read
Nvidia Is Reportedly Buying Hugging Face for $12.9 Billion
sizzlebop profile

Nvidia Is Reportedly Buying Hugging Face for $12.9 Billion

#news #ai #llm #nvidia
8
Comments 1
4 min read
DGX Spark (GB10) bare-metal vLLM: the install that works, two landmines, measured timings
conatusai profile
Jahn

DGX Spark (GB10) bare-metal vLLM: the install that works, two landmines, measured timings

#nvidia #llm #gpu #vllm
1
Comments
2 min read
Cerebras CS-4 vs NVIDIA GB300 NVL72: What the 30x Inference Speed Claim Means for Your Agents
jamilxt profile

Cerebras CS-4 vs NVIDIA GB300 NVL72: What the 30x Inference Speed Claim Means for Your Agents

#ai #machinelearning #nvidia #infrastructure
Comments
7 min read
🏗️ Nvidia is backing an enormous OpenAI data-center buildout in Ohio
ashutosh_maurya profile

🏗️ Nvidia is backing an enormous OpenAI data-center buildout in Ohio

#nvidia #ai #openai #datacenter
Comments
1 min read
NVIDIA Unveils Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4: A Deployment-Optimized Hybrid MoE LLM
pneumetron profile

NVIDIA Unveils Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4: A Deployment-Optimized Hybrid MoE LLM

#nvidia #nemotron3puzzle #llm #moe
Comments
4 min read
NOOA: What If an AI Agent Was Just a Python Object?
gaurav_talesara profile

NOOA: What If an AI Agent Was Just a Python Object?

#ai #python #nvidia #agentskills
1
Comments
6 min read
Nvidia's Router Is the Part of Agents Everyone Keeps Rebuilding
reidmarlow profile

Nvidia's Router Is the Part of Agents Everyone Keeps Rebuilding

#ai #agents #nvidia #programming
2
Comments
4 min read
Nvidia Is Buying the Part of AI Nobody Can pip install
reidmarlow profile

Nvidia Is Buying the Part of AI Nobody Can pip install

#ai #nvidia #cloud #infrastructure
2
Comments 4
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.