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 12, 11:00 UTC
add skip_reading_prefix_cache in repr for PoolingParams (#29620)
果冻虾仁 committed
Nov 28, 2025 at 01:21 UTC
d45269b37844b992dc4b34c0509ad8319bc043e5
1 file changed
+1
vllm/pooling_params.py
+1
@@ -219,6 +219,7 @@ class PoolingParams(
219
f"step_tag_id={self.step_tag_id}, "
220
f"returned_token_ids={self.returned_token_ids}, "
221
f"requires_token_ids={self.requires_token_ids}, "
222
+ f"skip_reading_prefix_cache={self.skip_reading_prefix_cache}, "
223
f"extra_kwargs={self.extra_kwargs})"
224
)
225