re-activate automatic testing

fix typo in cached models docs
2026-02-12 08:45:54 +01:00 · 2026-02-11 02:14:18 +01:00
2 changed files with 1 additions and 1 deletions
@@ -13,7 +13,7 @@ However, this will cause every worker to download the model from the Hugging Fac
 A naive way to cache the model would be to store it on a network volume in RunPod and reference the model files this way:

 ```bash
-hf /runpod-volume/model.gguf --ctx-size 4096 # etc...
+-m /runpod-volume/model.gguf --ctx-size 4096 # etc...
 ```

 Unfortunately, network volume performance is often not sufficient for loading large models, leading to long load times. RunPod introduced a [caching mechanism](https://docs.runpod.io/serverless/endpoints/model-caching) to solve this problem.
Author	SHA1	Message	Date
mags0ft	b24c32c024	re-activate automatic testing	2026-02-12 08:45:54 +01:00
mags0ftandGitHub	c7b115bec0	fix typo in cached models docs	2026-02-11 02:14:18 +01:00