Stories by sherlockxu

What Is InferenceOps

How to Beat the GPU CAP theorem in AI Inference

Meta's benchmarks for its new AI models are a bit misleading

Kai Scheduler: Kubernetes Native scheduler for AI workloads at large scale

OpenAI study finds links between ChatGPT use and loneliness

Survey shows 65% of organizations are still establishing their AI foundations

Show HN: Comfy-Pack: Making ComfyUI Workflows Shareable

AI: Red Hat's vision for an open source future

Meta under fire for 'polluting' open-source

Top Open-Source Vision Language Models

Exploring the World of Open-Source Text-to-Speech Models

What one AI CEO learned by working 20 feet from Apple's Steve Jobs

From Ollama to OpenLLM: Running LLMs in the Cloud

Documentation Salary Survey 2023 Results

Knowledge Graph vs. Vector RAG

Tech layoffs: 98,000 impacted as Apple, Google, others continue job cuts

Stable Diffusion 3: Text Master, Prone Problems?

Benchmarking LLM Inference Back Ends: VLLM, LMDeploy, MLC-LLM, TRT-LLM, and TGI

A Guide to Model Composition

Building RAG with Open-Source and Custom AI Models

1
2
3
4