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 15, 22:15 UTC
[Bugfix] Revert inspection code in #13743 (#13832)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Feb 26, 2025 at 00:18 UTC
f4133ce4e5b1aece3df646d912e11b6e6acc51ae
1 file changed
-6
vllm/model_executor/models/registry.py
-6
@@ -364,12 +364,6 @@ class _ModelRegistry:
364
raise ValueError(msg)
365
366
model = _LazyRegisteredModel(*split_str)
367
-
368
- try:
369
- model.inspect_model_cls()
370
- except Exception as exc:
371
- msg = f"Unable to inspect model {model_cls}"
372
- raise RuntimeError(msg) from exc
367
elif isinstance(model_cls, type) and issubclass(model_cls, nn.Module):
368
model = _RegisteredModel.from_model_cls(model_cls)
369
else: