[Docs] Classify PD disaggregation as an experimental feature (#6115)

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu authored and GitHub committed 2026-08-17 17:38:44 +08:00
1 parent 5d09cf27a9
commit 265d80b4dd
6 files changed
+151 -178

No files matched your search

-4
View File
@@ -14,10 +14,6 @@ For introduction, please check [Introduction for stage config](./stage_configs.m
- **[GPU Memory Calculation and Configuration](./gpu_memory_utilization.md)** - Guide on how to calculate memory requirements and set up `gpu_memory_utilization` for optimal performance
## Multi-Stage Recipes
- **[Prefill-Decode Disaggregation](./pd_disaggregation.md)** - How to derive a PD-aware Qwen3-Omni stage config from the default config without introducing another bundled YAML
## Optimization Features
- **[Diffusion Features Overview](../user_guide/diffusion_features.md)** - Complete overview of all diffusion model features and supported models