DEV Community

Machine Learning

A branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
How FlashAttention Actually Works: Tiling, SRAM Reuse, and Why It's 10x Faster

How FlashAttention Actually Works: Tiling, SRAM Reuse, and Why It's 10x Faster

Comments
3 min read
Serving Iris-3B Turbo: the 42 GB repo, the 21 GB of VRAM and the 8 MB payload limit

Serving Iris-3B Turbo: the 42 GB repo, the 21 GB of VRAM and the 8 MB payload limit

Comments
5 min read
Stop Calling an LLM for Every Ticket: Compile the Decision Once, Then Run It Locally

Stop Calling an LLM for Every Ticket: Compile the Decision Once, Then Run It Locally

1
Comments
8 min read
Why the same face doesn't score 1.0 – lessons from building a face-similarity search in Python

Why the same face doesn't score 1.0 – lessons from building a face-similarity search in Python

Comments
5 min read
Ling-3.1-flash and the 7:1 hybrid: how much KV cache does a 560B model need at 1M tokens?

Ling-3.1-flash and the 7:1 hybrid: how much KV cache does a 560B model need at 1M tokens?

Comments
10 min read
LFM2.5-24B-A2B on Your Own Hardware: The RAM, KV Cache and Bandwidth Budget

LFM2.5-24B-A2B on Your Own Hardware: The RAM, KV Cache and Bandwidth Budget

Comments
11 min read
We Ran 8 Texts Through an AI Detector. It Called a Human Wikipedia Paragraph 99% AI.

We Ran 8 Texts Through an AI Detector. It Called a Human Wikipedia Paragraph 99% AI.

Comments
3 min read
Beyond Connected Sensors: How AI and IoT Are Transforming Industrial Decision-Making 🤖

Beyond Connected Sensors: How AI and IoT Are Transforming Industrial Decision-Making 🤖

Comments
5 min read
Qwen3-4B deslop corta las muletillas de IA de 121 a 12,5 por 1000 palabras

Qwen3-4B deslop corta las muletillas de IA de 121 a 12,5 por 1000 palabras

Comments
12 min read
來訓練自己的 Jev 模型吧:)

來訓練自己的 Jev 模型吧:)

Comments
2 min read
RunPod vs Vast.ai (2026): Real H100 & A100 Effective Cost After Cold-Start, NVMe Storage & Bandwidth Billing

RunPod vs Vast.ai (2026): Real H100 & A100 Effective Cost After Cold-Start, NVMe Storage & Bandwidth Billing

Comments
11 min read
【Python Streamlit】ローカルPC(CPU)で動かす自分だけのAI画像生成Webアプリ

【Python Streamlit】ローカルPC(CPU)で動かす自分だけのAI画像生成Webアプリ

Comments
1 min read
ROC-AUC vs PR-AUC: Why Rare Events Need More Than One Metric

ROC-AUC vs PR-AUC: Why Rare Events Need More Than One Metric

Comments
8 min read
Reflection AI's Beam: How a 501B MoE Model Learns to Think in Fewer Tokens

Reflection AI's Beam: How a 501B MoE Model Learns to Think in Fewer Tokens

Comments
5 min read
DeepInfer: What's Actually Inside DeepSeek's Newly Open-Sourced Inference Engine

DeepInfer: What's Actually Inside DeepSeek's Newly Open-Sourced Inference Engine

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