* [vLLM Simulator v0.9.1](https://github.com/llm-d/llm-d-inference-sim) – Lightweight simulator emulating LLM inference HTTP endpoints and Prometheus metrics for development and testing.

* [KV-Cache v0.8.1](https://github.com/llm-d/llm-d-kv-cache) – Distributed KV tensor cache indexer and routing library for KV-cache-aware LLM inference scheduling.