Qwen3-Next:Update the gpu-memory-utilization parameter to 0.7 (#5129)

### What this PR does / why we need it?
Update the gpu-memory-utilization parameter to 0.7

- vLLM version: v0.12.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9

---------

Signed-off-by: ming1212 <2717180080@qq.com>
Signed-off-by: ming1212 <104972349+ming1212@users.noreply.github.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
This commit is contained in:
ming1212andMengqing Cao authored and GitHub committed 2025-12-18 15:16:33 +08:00
1 parent ef8157a5f2
commit 9268ad11e3
1 file changed
+4 -1
+4 -1
View File
@@ -19,6 +19,9 @@ Refer to [feature guide](../user_guide/feature_guide/index.md) to get the featur
Download Link for the `Qwen3-Next-80B-A3B-Instruct` Model Weights: [Download model weight](https://modelers.cn/models/Modelers_Park/Qwen3-Next-80B-A3B-Instruct/tree/main)
## Deployment
If the machine environment is an Atlas 800I A3(64G*16), the deployment approach stays identical.
### Run docker container
```{code-block} bash
@@ -92,7 +95,7 @@ Run the following script to start the vLLM server on multi-NPU:
For an Atlas A2 with 64 GB of NPU card memory, tensor-parallel-size should be at least 4, and for 32 GB of memory, tensor-parallel-size should be at least 8.
```bash
vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --tensor-parallel-size 4 --max-model-len 4096 --gpu-memory-utilization 0.85 --compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY"}'
vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --tensor-parallel-size 4 --max-model-len 4096 --gpu-memory-utilization 0.7 --compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY"}'
```
Once your server is started, you can query the model with input prompts.