[Docs] Add docs for disaggregated deployment (#6700)

* add docs for disaggregated deployment

* pre-commit run for style check

* update docs
This commit is contained in:
Jingfeng Wu
2026-04-01 19:27:09 +08:00
committed by GitHub
parent ceaf5df350
commit 3b564116d5
6 changed files with 513 additions and 0 deletions
+2
View File
@@ -1,5 +1,7 @@
[English](../../features/disaggregated.md)
[最佳实践](../best_practices/Disaggregated.md)
# 分离式部署
LLM大模型推理分为Prefill和Decode两个阶段,分别为计算密集型和访存密集型。