A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 00:30 UTC
use stringData in secret yaml to store huggingface token (#25685)
Signed-off-by: yiting.jiang <yiting.jiang@daocloud.io>
yitingdc committed
Oct 30, 2025 at 15:47 UTC
31b55ffc62189b32dac15fb7c00dba20e3573168
1 file changed
+5
-2
docs/deployment/k8s.md
+5
-2
@@ -49,11 +49,14 @@ First, create a Kubernetes PVC and Secret for downloading and storing Hugging Fa
49
metadata:
50
name: hf-token-secret
51
type: Opaque
52
- data:
53
- token: $(HF_TOKEN)
52
+ stringData:
53
+ token: "REPLACE_WITH_TOKEN"
54
EOF
55
```
56
57
+Here, the `token` field stores your **Hugging Face access token**. For details on how to generate a token,
58
+see the [Hugging Face documentation](https://huggingface.co/docs/hub/en/security-tokens).
59
+
60
Next, start the vLLM server as a Kubernetes Deployment and Service:
61
62
??? console "Config"