DEV Community

# gpu

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
RTX 4090 Cooling, LLM KV Cache Quantization, & Deepseek V4 Flash Models

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

Comments
3 min read
GPU Prices Up 48% in Two Months. I Run LLMs in My Garage.

GPU Prices Up 48% in Two Months. I Run LLMs in My Garage.

Comments
3 min read
Deepseek TileKernels, RTX 3090 LLM Benchmarks & Nvidia Inference Dashboard

Deepseek TileKernels, RTX 3090 LLM Benchmarks & Nvidia Inference Dashboard

Comments
3 min read
Production GPU Training is 34% Slower. Show Me Why

Production GPU Training is 34% Slower. Show Me Why

Comments
6 min read
CUDA Triton Optimization, RTX Remix VFX Update, and VSR Benchmarks

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

Comments
4 min read
I Built a Local AI VRAM Calculator & GPU Planner (Beta)

I Built a Local AI VRAM Calculator & GPU Planner (Beta)

7
Comments 2
3 min read
AI GPU Cost Audit for Indian AI Startups: H100, Inferentia2 & Spot Economics (2026)

AI GPU Cost Audit for Indian AI Startups: H100, Inferentia2 & Spot Economics (2026)

Comments
6 min read
Optimizing MPI Performance (Real Examples)

Optimizing MPI Performance (Real Examples)

Comments
3 min read
Why GPU Clusters Bleed Money in Kubernetes (and How to Stop It)

Why GPU Clusters Bleed Money in Kubernetes (and How to Stop It)

Comments
6 min read
How I built an AI platform in a country where the Western ones aren’t for sale

How I built an AI platform in a country where the Western ones aren’t for sale

Comments
6 min read
NVIDIA Pushes GPU Tech: DLSS 4.5, Streamline 2.11.1 SDKs & RTX Remix Updates

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

Comments
3 min read
Agent + MCP + eBPF: 10,869 CUDA Kernel Events, Now Queryable

Agent + MCP + eBPF: 10,869 CUDA Kernel Events, Now Queryable

1
Comments
5 min read
How are people comparing GPU prices across providers?

How are people comparing GPU prices across providers?

Comments
1 min read
Local LLM on NVIDIA GPU vs Cloud API: A Real Cost Analysis

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

Comments
5 min read
NVIDIA Vera Rubin 192GB SOCAMM2 Memory, SASS Reverse Engineering, & CUDA Kernel Dev

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

Comments
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.