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, 05:30 UTC
[CI] fix docs build failed (#27082)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Oct 17, 2025 at 15:53 UTC
acb1bfa601c60411728b925a4b2bfc3c516310ab
1 file changed
+1
-1
docs/models/supported_models.md
+1
-1
@@ -116,7 +116,7 @@ Here is what happens in the background when this model is loaded:
116
117
1. The config is loaded.
118
2. `MyModel` Python class is loaded from the `auto_map` in config, and we check that the model `is_backend_compatible()`.
119
-3. `MyModel` is loaded into one of the Transformers backend classes in [vllm/model_executor/models/transformers.py](../../vllm/model_executor/models/transformers.py) which sets `self.config._attn_implementation = "vllm"` so that vLLM's attention layer is used.
119
+3. `MyModel` is loaded into one of the Transformers backend classes in [vllm/model_executor/models/transformers](../../vllm/model_executor/models/transformers) which sets `self.config._attn_implementation = "vllm"` so that vLLM's attention layer is used.
120
121
That's it!
122