✕ Clear all filters
10 articles
▶ Videos →

📰 Dev.to · Dev Yadav

10 articles · Updated every 3 hours · View all reads

All Articles 116,875Blog Posts 125,002Tech Tutorials 29,861Research Papers 23,513News 17,243 ⚡ AI Lessons
The Demo Was One User. Then Batch Size Became Real.
Dev.to · Dev Yadav 📐 ML Fundamentals ⚡ AI Lesson 3mo ago
The Demo Was One User. Then Batch Size Became Real.
The demo worked because the test was one user, one prompt, one response. Then real usage showed up,...
View lesson → + Playlist
4-bit Quantization Does Not Make VRAM Problems Go Away
Dev.to · Dev Yadav 📐 ML Fundamentals ⚡ AI Lesson 3mo ago
4-bit Quantization Does Not Make VRAM Problems Go Away
A lot of people hear 4-bit quantization and mentally convert that into this model should run anywhere...
View lesson → + Playlist
KV Cache Is Why Your Model Fit Until It Did Not
Dev.to · Dev Yadav 💻 AI-Assisted Coding ⚡ AI Lesson 3mo ago
KV Cache Is Why Your Model Fit Until It Did Not
The model loaded. The first prompt worked. Then longer prompts or multiple users showed up, and...
View lesson → + Playlist
7B Parameters Does Not Mean 8GB VRAM Is Enough
Dev.to · Dev Yadav 💻 AI-Assisted Coding ⚡ AI Lesson 3mo ago
7B Parameters Does Not Mean 8GB VRAM Is Enough
A lot of people see 7B and assume 8GB VRAM should be enough. Then they load the model, increase...
View lesson → + Playlist
The Model Was Cheap. The Retries Became the Bill.
Dev.to · Dev Yadav ⚡ AI Lesson 3mo ago
The Model Was Cheap. The Retries Became the Bill.
The hourly price did not look scary. What hurt was running the same job again, reloading the same...
View lesson → + Playlist
The Tutorial Used Tiny Prompts. Your Real Prompts Did Not.
Dev.to · Dev Yadav 🧠 Large Language Models ⚡ AI Lesson 3mo ago
The Tutorial Used Tiny Prompts. Your Real Prompts Did Not.
The tutorial looked smooth because the prompt was tiny. Then you used the real prompt your app...
View lesson → + Playlist
The Demo Worked on a 7B Model. Production Traffic Changed the Math.
Dev.to · Dev Yadav 📐 ML Fundamentals ⚡ AI Lesson 3mo ago
The Demo Worked on a 7B Model. Production Traffic Changed the Math.
The demo looked fine on a small model with one user. Then real traffic showed up, latency got ugly,...
View lesson → + Playlist
The Cheapest GPU Looked Smart. Then the Job Took All Night.
Dev.to · Dev Yadav 📐 ML Fundamentals ⚡ AI Lesson 3mo ago
The Cheapest GPU Looked Smart. Then the Job Took All Night.
The hourly price looked great, so the cheapest GPU felt like the responsible choice. Then the run...
View lesson → + Playlist
Your Model Loaded Fine. Then Context Length Broke the GPU Plan.
Dev.to · Dev Yadav 📐 ML Fundamentals ⚡ AI Lesson 3mo ago
Your Model Loaded Fine. Then Context Length Broke the GPU Plan.
The model loaded. The notebook worked. Then you increased context length, batch size, or both, and...
View lesson → + Playlist
Best GPU Rental for AI Training in India
Dev.to · Dev Yadav 🧠 Large Language Models ⚡ AI Lesson 3mo ago
Best GPU Rental for AI Training in India
Training LLMs? Fine-tuning models? Here's which GPU you actually need (and which ones are...
View lesson → + Playlist