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, 09:45 UTC
[Bugfix]Change the exception thrown by call_hf_processor from RuntimeError to ValueError (#18181)
Signed-off-by: Abatom <abzhonghua@gmail.com>
Zhonghua Deng committed
May 16, 2025 at 00:01 UTC
fadb8d5c2df1c24d891aeccfb0b11de6e03e9f27
1 file changed
+1
-1
vllm/inputs/registry.py
+1
-1
@@ -159,7 +159,7 @@ class InputProcessingContext(InputContext):
159
msg = (f"Failed to apply {type(hf_processor).__name__} "
160
f"on data={data} with kwargs={merged_kwargs}")
161
162
- raise RuntimeError(msg) from exc
162
+ raise ValueError(msg) from exc
163
164
165
class DummyData(NamedTuple):