Artificial Intelligence

Machine Learning

Large Language Models

Vllm

Explore recommended reads, summarized by AI

Implementation and Performance

Technical approaches to deploying and optimizing vLLM for inference workloads.

Framework Comparisons and RAG Applications

Inference Optimization Techniques

Popular this week

In

Towards AI

by

Cameron Jagoe

I Ran One Local Agent for 22 Hours on a Single DGX Spark. It Timed Out 1,330 Times.

Alexa Griffith

Running vLLM Hello World on a Mac

Michael Galarnyk

Parameter-Efficient LLM Fine-Tuning in Practice: LoRA, QLoRA, Flyte, and vLLM

Ravish Khullar

Complete Production Guide: Deploying AgentGateway with vLLM on Kubernetes

Agent Native

Running Multiple vLLM Models on One GPU

Selected by Medium

In

Google Cloud - Community

by

Federico Iezzi

Your KV Cache Transfer Is 100x Slower Than It Should Be

Latest stories

In

Profit4Cloud — AI

by

Iddo Kerkhof

Pushing the DGX Spark to the Max with Qwen 3.6 and 3.8 Side by Side

Andolasoft

Air-Gapped AI Analytics: Apache Superset with Local LLMs (Ollama and vLLM)

Allen Kuo (kwyshell)

Another Route to vLLM-Style Serving, Part 2: CPU, Vulkan, and GGUF Across Platforms

Allen Kuo (kwyshell)

vLLM 式 serving 的另一條路（下）：CPU、Vulkan 與 GGUF，走向多平台

Rishabh Nimje

Stop Recomputing What Your AI Agent Already Knows: Prefix Caching with SGLang and vLLM

See more stories

Who to follow

Popular this week

In

Towards AI

by

Cameron Jagoe

I Ran One Local Agent for 22 Hours on a Single DGX Spark. It Timed Out 1,330 Times.

Alexa Griffith

Running vLLM Hello World on a Mac

Michael Galarnyk

Parameter-Efficient LLM Fine-Tuning in Practice: LoRA, QLoRA, Flyte, and vLLM

Ravish Khullar

Complete Production Guide: Deploying AgentGateway with vLLM on Kubernetes

Agent Native

Running Multiple vLLM Models on One GPU

Selected by Medium

In

Google Cloud - Community

by

Federico Iezzi

Your KV Cache Transfer Is 100x Slower Than It Should Be

Latest stories

In

Profit4Cloud — AI

by

Iddo Kerkhof

Pushing the DGX Spark to the Max with Qwen 3.6 and 3.8 Side by Side

Andolasoft

Air-Gapped AI Analytics: Apache Superset with Local LLMs (Ollama and vLLM)

Allen Kuo (kwyshell)

Another Route to vLLM-Style Serving, Part 2: CPU, Vulkan, and GGUF Across Platforms

Allen Kuo (kwyshell)

vLLM 式 serving 的另一條路（下）：CPU、Vulkan 與 GGUF，走向多平台

Rishabh Nimje

Stop Recomputing What Your AI Agent Already Knows: Prefix Caching with SGLang and vLLM

See more stories

Who to follow