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

Docs: Remove deprecated --task parameter for embedding models (#5257)

Browse Source 
Fixes #3376

- Remove --task embed from vllm serve command in Qwen3_embedding.md
- Remove task='embed' parameter from LLM constructor in Python example

The --task parameter has been deprecated in recent vLLM versions 
in favor of automatic model type detection.
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: hu-qi <huqi1024@gmail.com>
This commit is contained in:
huqi
2025-12-30 16:09:07 +08:00
committed by GitHub
parent 71f729a661
commit c85cc045f8
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/source/tutorials/Qwen3_embedding.md
View File

@@ -30,7 +30,7 @@ Using the Qwen3-Embedding-8B model as an example, first run the docker container
### Online Inference ### Online Inference
```bash ```bash
vllm serve Qwen/Qwen3-Embedding-8B --task embed --host 127.0.0.1 --port 8888 vllm serve Qwen/Qwen3-Embedding-8B --runner pooling --host 127.0.0.1 --port 8888
``` ```
Once your server is started, you can query the model with input prompts. Once your server is started, you can query the model with input prompts.
@@ -71,7 +71,6 @@ if __name__=="__main__":
input_texts = queries + documents input_texts = queries + documents
model = LLM(model="Qwen/Qwen3-Embedding-8B", model = LLM(model="Qwen/Qwen3-Embedding-8B",
task="embed",
distributed_executor_backend="mp") distributed_executor_backend="mp")
outputs = model.embed(input_texts) outputs = model.embed(input_texts)