Voozh

3 min read

👁 jaychkdsk profile

Jay Grider

Jun 12

How to Build a Secure Homelab for LLM Inference

#homelab #llmsecurity #inference #supplychain

Add Comment

4 min read

👁 peremptory profile

Peremptory

Jun 11

Google's DiffusionGemma Generates Text Sideways

#modelrelease #architecture #opensource #inference

Add Comment

3 min read

👁 tech_nuggets profile

Tech_Nuggets

Jun 5

Speculative decoding: when and why it actually speeds up inference

#llm #ai #inference #performance

👁 Image
1 reaction

Add Comment

9 min read

👁 jangwook_kim_e31e7291ad98 profile

Jangwook Kim

May 11

ReFlect: Training-Free Error Recovery for Long-Horizon LLM Reasoning

#llmreasoning #agents #inference #arxiv2026

Add Comment

4 min read

👁 bruno_juca_7038c22bcca1db profile

Bruno Juca

May 10

Why Most Browser AI Demos Fail on Real Hardware

#ai #inference #hardware #benchmark

Add Comment

4 min read

👁 david_aronchick_ea415de50 profile

David Aronchick

May 5

The Inference Inversion

#distributedcomputing #edgecomputing #nvidia #inference

Add Comment

7 min read

👁 steriani_karamanlis_ad61a profile

Steriani Karamanlis

May 12

First Confirmed Directional Move on the AI Inference Frontier Index in 2026

#ai #llm #inference #pricing

Add Comment

4 min read

👁 DigitalOcean logo
👁 andrew_d profile

Andrew Dugan

for DigitalOcean

May 21

Tutorial: This AI Now Tells You if a Meeting Could Be an Email

#ai #tutorial #agentskills #inference

👁 Image
3 reactions

Add Comment

8 min read

👁 DigitalOcean logo
👁 james_skelton profile

James Skelton

for DigitalOcean

May 19

Tutorial: Build a Cost-Aware AI Support Triage API

#ai #tutorial #api #inference

👁 Image
3 reactions

1 comment

13 min read

👁 gabrielanhaia profile

Gabriel Anhaia

Apr 26

Muse Spark beats Llama 4 with 10x less compute. Here's how.

#ai #llm #architecture #inference

Add Comment

7 min read

👁 gounthar profile

Bruno Verachten

Apr 22

First Words: LLM Inference on RISC-V

#bananapi #benchmark #inference #llamacpp

Add Comment

9 min read

👁 thousand_miles_ai profile

Thousand Miles AI

May 23

BeeLlama v0.2.0: 164 tok/s on a 27B model, one RTX 3090

#ai #llm #inference #opensource

Add Comment

3 min read

👁 thousand_miles_ai profile

Thousand Miles AI

May 19

Your AI speed benchmark is measuring the one workload you don't run

#discuss #ai #llm #inference

Add Comment

3 min read

👁 berkan_sesen profile

Berkan Sesen

Apr 13

Gaussian Process Regression: The Bayesian Approach to Curve Fitting

#bayesian #supervisedlearning #probabilistic #inference

Add Comment

13 min read

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

URL: https://dev.to/t/inference

⇱ Inference - DEV Community

Can You Tell When an LLM API Swaps in a Cheaper Model?

How to Build a Secure Homelab for LLM Inference

Google's DiffusionGemma Generates Text Sideways

Speculative decoding: when and why it actually speeds up inference

ReFlect: Training-Free Error Recovery for Long-Horizon LLM Reasoning

Why Most Browser AI Demos Fail on Real Hardware

The Inference Inversion

First Confirmed Directional Move on the AI Inference Frontier Index in 2026

Tutorial: This AI Now Tells You if a Meeting Could Be an Email

Tutorial: Build a Cost-Aware AI Support Triage API

Muse Spark beats Llama 4 with 10x less compute. Here's how.

First Words: LLM Inference on RISC-V

BeeLlama v0.2.0: 164 tok/s on a 27B model, one RTX 3090

Your AI speed benchmark is measuring the one workload you don't run

Gaussian Process Regression: The Bayesian Approach to Curve Fitting