EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[CI]Add EPLB CI. (#3568)

Browse Source 
### What this PR does / why we need it?
1.Add eplb ci to check the change of eplb feature.
2.Add param checking of eplb params. 
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
Qwen in A3.


- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: offline0806 <3337230449@qq.com>
Co-authored-by: offline0806 <3337230449@qq.com>
This commit is contained in:
offline893
2025-10-21 22:58:02 +08:00
committed by GitHub
parent 4c9af353ee
commit e916265b2b
11 changed files with 461 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/user_guide/feature_guide/eplb_swift_balancer.md
View File

@@ -16,7 +16,7 @@ Expert balancing for MoE models in LLM serving is essential for optimal performa
### Dynamic EPLB
We need to add environment variable `export DYNAMIC_EPLB=true` to enable vllm eplb. Enable dynamic balancing with auto-tuned parameters. Adjust num_iterations_eplb_update and num_wait_worker_iterations based on workload patterns.
We need to add environment variable `export DYNAMIC_EPLB="true"` to enable vllm eplb. Enable dynamic balancing with auto-tuned parameters. Adjust num_iterations_eplb_update and num_wait_worker_iterations based on workload patterns.
```shell
vllm serve Qwen/Qwen3-235B-A22 \
@@ -32,7 +32,7 @@ vllm serve Qwen/Qwen3-235B-A22 \
### Static EPLB
#### Initial Setup (Record Expert Map)
We need to add environment variable `export EXPERT_MAP_RECORD=true` to record expert map.Generate the initial expert distribution map using expert_map_record_path. This creates a baseline configuration for future deployments.
We need to add environment variable `export EXPERT_MAP_RECORD="true"` to record expert map.Generate the initial expert distribution map using expert_map_record_path. This creates a baseline configuration for future deployments.
```shell
vllm serve Qwen/Qwen3-235B-A22 \