# vLLM upgrades its EPD encoder disaggregation with lower latency and higher throughput

> Original title: vLLM EPD, now upgraded 🚀

- Source: vLLM
- Published: 2026-11-11T10:03:43.000Z
- Bad Influence: https://badinfluence.news/items/uhmyvqniwedcklzjcq5awnh5f
- Original: https://x.com/vllm_project/status/2120457435152613455

## Summary

vLLM says its latest EPD encoder disaggregation improvements deliver lower TTFT and higher throughput per GPU, counting all encoder GPUs. The upgrade is integrated with vLLM Router, SMG, and llm-d. The post links to a blog with details.

## Post

vLLM EPD, now upgraded 🚀

DeepInfer demonstrated the value of EPD disaggregation. vLLM’s latest EPD improvements deliver lower TTFT and higher throughput per GPU, counting all encoder GPUs, integrated with vLLM Router, SMG, and llm-d!

Read more here!👇
https://vllm.ai/blog/2026-11-11-encoder-disaggregation-epd