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

[Doc]Delete equals sign (#4537)

Browse Source 
### What this PR does / why we need it?
Delete equals sign in doc
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
ut


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: herizhen <you@example.com>
Co-authored-by: herizhen <you@example.com>
This commit is contained in:
herizhen
2025-11-28 17:09:26 +08:00
committed by GitHub
parent 366d2d95e8
commit 3199fe8350
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/developer_guide/feature_guide/Multi_Token_Prediction.md
View File

@@ -6,7 +6,7 @@ MTP boosts inference performance by parallelizing the prediction of multiple tok
## How to Use MTP
To enable MTP for DeepSeek-V3 models, add the following parameter when starting the service:
`--speculative_config={"method": "deepseek_mtp", "num_speculative_tokens": 1, "disable_padded_drafter_batch": False}`
--speculative_config ' {"method": "deepseek_mtp", "num_speculative_tokens": 1, "disable_padded_drafter_batch": False} '
- `num_speculative_tokens`: The number of speculative tokens which enable model to predict multiple tokens at once, if provided. It will default to the number in the draft model config if present, otherwise, it is required.
- `disable_padded_drafter_batch`: Disable input padding for speculative decoding. If set to True, speculative input batches can contain sequences of different lengths, which may only be supported by certain attention backends. This currently only affects the MTP method of speculation, default is False.