tclf90 commited on
Commit
a5ea107
·
verified ·
1 Parent(s): b78a35e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -13,18 +13,19 @@ base_model_relation: quantized
13
  Base Model: [Qwen/Qwen3-VL-30B-A3B-Instruct](https://www.modelscope.cn/models/Qwen/Qwen3-VL-30B-A3B-Instruct)
14
 
15
  ### 【Dependencies / Installation】
16
- As of **2025-10-04**, create a fresh Python environment and run:
17
  ```bash
18
- pip install -U pip uv
 
19
 
20
- # Install vLLM >= 0.11.0
21
  uv pip install -U vllm
22
 
23
  # Install Qwen-VL utility library (recommended for offline inference)
24
  uv pip install qwen-vl-utils==0.0.14
25
  ```
26
 
27
- [vLLM Installation Guide](https://docs.vllm.ai/projects/recipes/en/latest/Qwen/Qwen3-VL.html)
28
 
29
  ### 【vLLM Startup Command】
30
 
 
13
  Base Model: [Qwen/Qwen3-VL-30B-A3B-Instruct](https://www.modelscope.cn/models/Qwen/Qwen3-VL-30B-A3B-Instruct)
14
 
15
  ### 【Dependencies / Installation】
16
+ As of **2025-10-08**, create a fresh Python environment and run:
17
  ```bash
18
+ uv venv
19
+ source .venv/bin/activate
20
 
21
+ # Install vLLM >=0.11.0
22
  uv pip install -U vllm
23
 
24
  # Install Qwen-VL utility library (recommended for offline inference)
25
  uv pip install qwen-vl-utils==0.0.14
26
  ```
27
 
28
+ For more details, refer to [vLLM Official Qwen3-VL Guide](https://docs.vllm.ai/projects/recipes/en/latest/Qwen/Qwen3-VL.html)
29
 
30
  ### 【vLLM Startup Command】
31