[Docs] Mark PD disaggregation as experimental
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
1 parent
12f8168179
commit
c46abfef59
4 files changed
+15
-8
No files matched your search
@@ -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
|
||||
@@ -1,4 +1,8 @@
|
||||
# Prefill-Decode (PD) Disaggregation
|
||||
# Prefill-Decode (PD) Disaggregation (experimental)
|
||||
|
||||
!!! warning "Experimental"
|
||||
PD disaggregation support is experimental and currently documented only for
|
||||
Qwen3-Omni. Its configuration and behavior may change without notice.
|
||||
|
||||
PD disaggregation splits the Qwen3-Omni thinker into separate prefill and decode
|
||||
stages so prompt processing and token generation can run on different workers.
|
||||
|
||||
Reference in new issue
Block a user