EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[8/N] MoE Refactor: deprecate EPMoE (#11211)

Browse Source
This commit is contained in:
Cheng Wan
2025-10-07 21:51:41 -07:00
committed by GitHub
parent 7c3f07dbcb
commit 3c06b673af
19 changed files with 526 additions and 1808 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/advanced_features/server_arguments.md
View File

@@ -246,7 +246,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
|-----------|-------------|----------|
| `--ep-size` | The expert parallelism size. | 1 |
| `--moe-a2a-backend` | Select the backend for all-to-all communication for expert parallelism. | none |
| `--moe-runner-backend` | Select the runner backend for MoE. | 'triton' |
| `--moe-runner-backend` | Select the runner backend for MoE. | auto |
| `--deepep-mode` | Select the mode when enable DeepEP MoE, could be `normal`, `low_latency` or `auto`. Default is `auto`, which means `low_latency` for decode batch and `normal` for prefill batch. | auto |
| `--ep-num-redundant-experts` | Allocate this number of redundant experts in expert parallel. | 0 |
| `--ep-dispatch-algorithm` | The algorithm to choose ranks for redundant experts in EPLB. | None |