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 16, 07:00 UTC
[Doc] fix link for page that was renamed (#10455)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Nov 19, 2024 at 12:48 UTC
fd9f124971c58376ca294091951dfcc96cc03474
1 file changed
+1
-1
vllm/model_executor/model_loader/loader.py
+1
-1
@@ -105,7 +105,7 @@ def _initialize_model(vllm_config: VllmConfig, prefix: str = "") -> nn.Module:
105
msg = ("vLLM model class should accept `vllm_config` and `prefix` as "
106
"input arguments. Possibly you have an old-style model class"
107
" registered from out of tree and it is used for new vLLM version. "
108
- "Check https://docs.vllm.ai/en/latest/design/class_hierarchy.html "
108
+ "Check https://docs.vllm.ai/en/latest/design/arch_overview.html "
109
"for the design and update the model class accordingly.")
110
logger.warning(msg)
111
logger.warning(