nilig/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
IBM Research
Repositories
nilig/llm-d-router
Inference scheduler for llm-d
nilig/llm-d-benchmark
llm-d benchmark scripts and tooling
nilig/llm-d.github.io
Website for llm-d: This repository builds the website seen at llm-d.ai
nilig/llm-d-inference-payload-processor
Inference payload processor for llm-d
nilig/llm-d
Achieve state of the art inference performance with modern accelerators on Kubernetes
nilig/clawdchan
Let my Claude talk to yours.