DEV Community

#nvidia

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
From 1,540 to 15,338 Tokens per Second on a Single TPU Chip
rubenszmm profile

From 1,540 to 15,338 Tokens per Second on a Single TPU Chip

#googlecloudplatform #machinelearning #nvidia #tpu
Comments
20 min read
The dozen layers under a GPU pod
sachincool profile

The dozen layers under a GPU pod

#gpu #kubernetes #mlops #nvidia
Comments
14 min read
NVIDIA Nemotron 3 Ultra & GLM-5.2: The Open Model Flood Is Here (June 2026)
doremonai profile

NVIDIA Nemotron 3 Ultra & GLM-5.2: The Open Model Flood Is Here (June 2026)

#ai #opensource #machinelearning #nvidia
1
Comments
2 min read
Things I learned building my first multi-agent AI system on Azure + NVIDIA
sachin_magon profile

Things I learned building my first multi-agent AI system on Azure + NVIDIA

#ai #azure #nvidia #python
1
Comments 2
4 min read
Diffusion Language Models Are Here: Deep Dive into NVIDIA's Nemotron-Labs DLM Architecture
monuminu profile

Diffusion Language Models Are Here: Deep Dive into NVIDIA's Nemotron-Labs DLM Architecture

#ai #machinelearning #llm #nvidia
Comments
15 min read
I Built a Prompt Forging Engine with NVIDIA Llama 3.1 70B for Google Prompt Wars 2026
divyansh0208 profile

I Built a Prompt Forging Engine with NVIDIA Llama 3.1 70B for Google Prompt Wars 2026

#promptengineering #nvidia #python #webdev
3
Comments 2
3 min read
Nvidia's water-saving cooling fixes the wrong half of AI
induwara_ashinsana_9e4d5b profile

Nvidia's water-saving cooling fixes the wrong half of AI

#aisustainability #datacenters #nvidia
Comments
4 min read
Nvidia wants enterprises to run agents safely. NemoClaw is how.
thegatewayguy profile

Nvidia wants enterprises to run agents safely. NemoClaw is how.

#ai #agents #nvidia #devops
Comments
3 min read
⚡️Self-Hosting Experience with Jetson Orin Nano and Ollama 🦙
annavi11arrea1 profile

⚡️Self-Hosting Experience with Jetson Orin Nano and Ollama 🦙

#ubuntu #nvidia #webdev #ai
11
Comments
8 min read
'"An LLM and a harness": Nvidia''s simple thesis on what agents actually are'
thegatewayguy profile

'"An LLM and a harness": Nvidia''s simple thesis on what agents actually are'

#ai #llm #agents #nvidia
Comments 1
2 min read
nvidia-peermem "Invalid argument" on Ubuntu — Fix GPUDirect RDMA with DMA-BUF
fpolica91 profile

nvidia-peermem "Invalid argument" on Ubuntu — Fix GPUDirect RDMA with DMA-BUF

#nvidia #nvidiapeermem #ai #hpc
3
Comments
3 min read
Bypassing the OS to Run LLMs: What I Learned Building a Firmware-Centric Runtime
rotsl profile

Bypassing the OS to Run LLMs: What I Learned Building a Firmware-Centric Runtime

#llm #nvidia #cuda #firmware
Comments
5 min read
12B Gemma 4 QAT Deployment with GCE, NVIDIA L4, MCP, and Antigravity CLI
xbill profile

12B Gemma 4 QAT Deployment with GCE, NVIDIA L4, MCP, and Antigravity CLI

#mcps #qat #gemma4 #nvidia
6
Comments
16 min read
Two Qwen3 Models on One DGX Spark: The Residency Math for Local LLM Coding
ric03uec profile

Two Qwen3 Models on One DGX Spark: The Residency Math for Local LLM Coding

#localllm #vllm #ai #nvidia
1
Comments
5 min read
Stop Paying $20/month. Use NVIDIA Build: 80+ Free AI Models
lorenzojkrl profile

Stop Paying $20/month. Use NVIDIA Build: 80+ Free AI Models

#ai #programming #nvidia #llm
31
Comments 5
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.