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

[Performance] Add async exponential while model executing (#4501)

Browse Source 
### What this PR does / why we need it?
Add a control to enable the exponential distribution operator
overlapping with model executing (default is OFF due to this feature
might not perform well on MOE models, i.e. For Qwen3-30B).
Enable async exponential overlapping will provides performance
improvement.
Also, overlapping the exponential operator with module execution can
cover the performance drop introduced by AICPU-version's exponential
operator.

**UPDATE**: (12/12)
Now our overlap will use the same stream that introduced in this pr:
#4908 .
We move the `do_async_exponential` from `model_runner_v1.py` to
`sampler.py`.
Now we are using `additional_config` to enable async exponential:
Add `"enable_async_exponential": 1` in `addition_config`.
Now we **ONLY** support default exponential/AI-CPU exponential, the old
`"enable_async_exponential": 2` option has been aborted to keep
consistency.

### Does this PR introduce _any_ user-facing change?
**YES**, added a new `additional_config` : `"enable_async_exponential":
1`.
When `enable_async_exponential` is set to 1, we enable the async
exponential and overlap with model runner.
When `enable_async_exponential` is set to 0 (default is 0), we disable
the async exponential, but exponential will still running on a different
stream using stream introduced in #4908.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: YuhanBai <yuhan.bai0830@gmail.com>
Signed-off-by: YuhanBai yuhan.bai0830@gmail.com
This commit is contained in:
YuhanBai
2025-12-20 21:23:21 +08:00
committed by GitHub
parent 58773af708
commit 5d02eed16f
5 changed files with 60 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/source/user_guide/configuration/additional_config.md
View File

@@ -42,6 +42,7 @@ The following table lists additional configuration options available in vLLM Asc
| `expert_map_record_path` | str | `None` | Save the expert load calculation results to a new expert table in the specified directory. |
| `init_redundancy_expert` | int | `0` | Specify redundant experts during initialization. |
| `dump_config` | str | `None` | Configuration file path for msprobe dump(eager mode). |
| `enable_async_exponential` | int | `0` | Whether to enable async exponential overlap. To enable async exponential, set this config to 1. |
The details of each configuration option are as follows: