minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[NPU] update npu doc (#22697)

Browse Source 
Co-authored-by: zhsurpass <zhsurpass@users.noreply.github.com>
This commit is contained in:
看海的人
2026-04-13 21:55:38 +08:00
committed by GitHub
co-authored by zhsurpass
parent d01b2bf257
commit 56c97c7738
1 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/platforms/ascend/ascend_npu_support_features.md
+5 -4
View File
@@ -405,11 +405,12 @@ click [Server Arguments](https://docs.sglang.io/advanced_features/server_argumen
## Encode prefill disaggregation ## Encode prefill disaggregation
| Argument | Defaults | Options | Server supported | | Argument | Defaults | Options | Server supported |
|------------------------------|--------------------|----------------------------------------------------------------|:----------------:| | --------------------------------------- | ------------------ | ---------------------------------------------------------------- |:----------------:|
| `--encoder-only` | `False` | bool flag<br/> (set to enable) | A2, A3 | | `--enable-adaptive-dispatch-to-encoder` | `False` | bool flag<br/> (set to enable adaptively dispatch) | A2, A3 |
| `--language-only` | `False` | bool flag<br/> (set to enable) | A2, A3 | | `--encoder-only` | `False` | bool flag<br/> (set to launch an encoder-only server) | A2, A3 |
| `--language-only` | `False` | bool flag<br/> (set to load weights for the language model only) | A2, A3 |
| `--encoder-transfer-backend` | `zmq_to_scheduler` | `zmq_to_scheduler`, <br/> `zmq_to_tokenizer`,<br/> `mooncake` | A2, A3 | | `--encoder-transfer-backend` | `zmq_to_scheduler` | `zmq_to_scheduler`, <br/> `zmq_to_tokenizer`,<br/> `mooncake` | A2, A3 |
| `--encoder-urls` | `[]` | List[str] | A2, A3 | | `--encoder-urls` | `[]` | List[str]<br/> (List of encoder server urls) | A2, A3 |
## Custom weight loader ## Custom weight loader