@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / fd9f124971
Fork 0

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(