Gpu - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

InferenceKey for InferenceKey

Oct 15

Same config.json, different serve command: what to check before serving AREX-2

#ai #llm #machinelearning #gpu

5 min read

Oct 15

Open weights don't make a 1T model cheap to run

#ai #llm #mistral #gpu

1 min read

Oct 14

Kandinsky 6.0 on a 16 GB GPU: the official recipe runs out of memory, and only the 29B model passed my Spanish test

#ai #machinelearning #gpu #benchmark

2 min read

Sanskriti Harmukh for Vultr

Oct 14

Installing K3s with ROCm GPU Operator on Ubuntu 24.04

#kubernetes #k3s #rocm #gpu

3 min read

Oct 14

Run GPU kernel tuning as an overnight search loop

#ai #gpu #performance #python

6 min read

Hacks.gr

Oct 14

Nvidia's new graphics cards are very expensive in Japan

#nvidia #hardware #gpu #ai

1 min read

lucanu

Oct 14

Building a Distributed GPU Cluster for LLM Inference on Idle Apple Silicon Macs

#gpu #llm #macos #distributed

2 min read

Oct 13

I got tired of checking GPU cloud pricing pages by hand, so I built a price index API

#gpu #cloud #api #llm

2 min read

Sanskriti Harmukh for Vultr

Oct 14

Configuring Smart Routing in NVIDIA Dynamo

#llm #nvidia #gpu #inference

19 min read

Sanskriti Harmukh for Vultr

Oct 14

Installing Docker with ROCm GPU Support on Ubuntu 24.04

#docker #rocm #gpu #ubuntu

3 min read

VoltageGPU

Oct 13

Verifying Intel TDX and NVIDIA GPU attestation from inside a rented VM, and what it can't prove

#security #python #gpu #ai

3 min read

NTCTech

Oct 13

GPU Passthrough Works. Can You Still Move the VM?

#virtualization #vmware #gpu #infrastructure

10 min read

Oct 13

The same H100 hour cost $1.26 or $0.22 per million tokens

#ai #llm #gpu #mlops

2 min read

orca forge

Oct 12

An 80GB H100, and only 3B of the model could keep up with conversation

#gpu #llm #moe #ai

5 min read

Oct 12

Ready is not warm: one SGLang cold start on a T4

#llm #gpu #mlops

2 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.