billxbf commited on
Commit
aa81b56
·
verified ·
1 Parent(s): ee6c76d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -17,9 +17,19 @@ This model is a light SFT version from Qwen/Qwen3-14B, aimed at stable generativ
17
 
18
  ## Serve with vllm
19
 
 
 
 
 
 
 
 
 
20
 
 
21
  ```
22
  vllm serve billxbf/Nano-Raccoon-Preview-1104 \
 
23
  --trust-remote-code \
24
  --host 0.0.0.0 \
25
  --port 8000
 
17
 
18
  ## Serve with vllm
19
 
20
+ **Single GPU**
21
+ ```
22
+ vllm serve billxbf/Nano-Raccoon-Preview-1104 \
23
+ --trust-remote-code \
24
+ --host 0.0.0.0 \
25
+ --port 8000
26
+ ```
27
+
28
 
29
+ **Use Tensor Parallel on 8xGPU**
30
  ```
31
  vllm serve billxbf/Nano-Raccoon-Preview-1104 \
32
+ --tensor-parallel-size 8 \
33
  --trust-remote-code \
34
  --host 0.0.0.0 \
35
  --port 8000