LLMs Articles | LavX News | LavX News

Inside Nano-vLLM: How Modern Inference Engines Transform Prompts into Tokens

Inside Nano-vLLM: How Modern Inference Engines Transform Prompts into Tokens

AutoBe's Hardcore Function Calling Benchmark Pushes LLM Backend Generation to New Limits

AutoBe's Hardcore Function Calling Benchmark Pushes LLM Backend Generation to New Limits

LLMs as Emacs Elisp Assistants: Reducing the Friction of Infinite Customization

LLMs as Emacs Elisp Assistants: Reducing the Friction of Infinite Customization

Arcee AI launches Trinity Large, a 400B-parameter open-weight model challenging Meta's Llama 4 Maverick

Arcee AI launches Trinity Large, a 400B-parameter open-weight model challenging Meta's Llama 4 Maverick

GNU gettext Reaches Version 1.0 After 30+ Years In Development - Adds LLM Features

GNU gettext Reaches Version 1.0 After 30+ Years In Development - Adds LLM Features

The Double-Edged Sword of AI-Assisted Code Porting: Lessons from Translating TinyEMU to Go

Turns out I was wrong about TDD

Turns out I was wrong about TDD

From 24 to 216: A Systematic Performance Engineering Journey for LLM-based TTS

From 24 to 216: A Systematic Performance Engineering Journey for LLM-based TTS

Small Language Models Narrow the Gap: Efficiency Challenges Scale in Generative AI

Small Language Models Narrow the Gap: Efficiency Challenges Scale in Generative AI

Baidu's ERNIE 5.0: A 2.4 Trillion Parameter MoE Model, But What Does It Actually Do?

Baidu's ERNIE 5.0: A 2.4 Trillion Parameter MoE Model, But What Does It Actually Do?

Why I Don't Have Fun With Claude Code

Why I Don't Have Fun With Claude Code

The best code is no code: composing APIs and CLIs in the era of LLMs

The best code is no code: composing APIs and CLIs in the era of LLMs

The End of One-Size-Fits-All LLM APIs: Why Workload-Specific Inference Is Taking Over

The End of One-Size-Fits-All LLM APIs: Why Workload-Specific Inference Is Taking Over