Inference

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

Cover image for Gaussian Process Regression: The Bayesian Approach to Curve Fitting

Berkan Sesen

Apr 13

Gaussian Process Regression: The Bayesian Approach to Curve Fitting

#bayesian #supervisedlearning #probabilistic #inference

13 min read

plasmon

Apr 7

Light Just Cut KV Cache Memory Traffic to 1/16th

#llm #photonics #semiconductor #inference

7 min read

Cover image for Google Dropped TurboQuant Two Weeks Ago. The Community Already Made It Usable.

Alan West

Apr 7

Google Dropped TurboQuant Two Weeks Ago. The Community Already Made It Usable.

#turboquant #locallm #inference #opensource

6 min read

Cover image for From MLE to Bayesian Inference: Why Your Estimate Needs a Prior

Berkan Sesen

Mar 29

From MLE to Bayesian Inference: Why Your Estimate Needs a Prior

#bayesian #inference #statistics #probabilistic

15 min read

Cover image for The EM Algorithm: An Intuitive Guide with the Coin Toss Example

Berkan Sesen

Mar 27

The EM Algorithm: An Intuitive Guide with the Coin Toss Example

#unsupervisedlearning #inference #optimisation #probabilistic

10 min read

Cover image for Maximum Likelihood Estimation from Scratch: From Coin Flips to Gaussians

Berkan Sesen

Mar 26

Maximum Likelihood Estimation from Scratch: From Coin Flips to Gaussians

#statistics #inference #optimisation #probabilistic

13 min read

MrJHSN

Mar 19

DGX Spark Inference Performance: Local LLM vs Cloud Benchmarks (2026)

#dgx #llm #inference #benchmark

5 min read

Artyom Kornilov

Mar 10

Estimating Operational Costs for CLIP-Based Image Search on 1 Million Images: Infrastructure Expenses Focused

#clip #gpu #inference #cost

12 min read

deharoalexandre-cyber

Apr 8

I built an Ollama alternative with TurboQuant, model groups, and multi-GPU support

#ai #llm #cpp #inference

4 min read

Custodia-Admin

Mar 13

How to Optimize AI Agent Costs — Inference, API Calls, and Infrastructure

#agents #costs #optimization #inference

3 min read

Cover image for Why Inference Compression Compounds for Modular Agents

Rotifer Protocol

Mar 31

Why Inference Compression Compounds for Modular Agents

#inference #compression #agents #gene

4 min read

Cover image for Model Serving Infrastructure: Building Scalable Inference

Matt Frank

Feb 23

Model Serving Infrastructure: Building Scalable Inference

#modelserving #inference #mlops

7 min read

Cover image for How to Lower Your AI Costs When Scaling Your Business

Jess Lulka for DigitalOcean

Feb 20

How to Lower Your AI Costs When Scaling Your Business

#ai #llm #inference

3 min read

seah-js

Feb 6

KV Cache Optimization — Why Inference Memory Explodes and How to Fix It

#ai #machinelearning #inference #optimization

3 min read

Cover image for I got SAM3 video tracking wrong: the session wasn’t the problem—my reprojection was

Daniel Romitelli

Mar 10

I got SAM3 video tracking wrong: the session wasn’t the problem—my reprojection was

#computervision #video #inference #tracking

7 min read

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

Forem

# inference

Gaussian Process Regression: The Bayesian Approach to Curve Fitting

Light Just Cut KV Cache Memory Traffic to 1/16th

Google Dropped TurboQuant Two Weeks Ago. The Community Already Made It Usable.

From MLE to Bayesian Inference: Why Your Estimate Needs a Prior

The EM Algorithm: An Intuitive Guide with the Coin Toss Example

Maximum Likelihood Estimation from Scratch: From Coin Flips to Gaussians

DGX Spark Inference Performance: Local LLM vs Cloud Benchmarks (2026)

Estimating Operational Costs for CLIP-Based Image Search on 1 Million Images: Infrastructure Expenses Focused

I built an Ollama alternative with TurboQuant, model groups, and multi-GPU support

How to Optimize AI Agent Costs — Inference, API Calls, and Infrastructure

Why Inference Compression Compounds for Modular Agents

Model Serving Infrastructure: Building Scalable Inference

How to Lower Your AI Costs When Scaling Your Business

KV Cache Optimization — Why Inference Memory Explodes and How to Fix It

I got SAM3 video tracking wrong: the session wasn’t the problem—my reprojection was