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, 09:45 UTC
add add_truncate_prompt_tokens in repr for PoolingParams (#29683)
果冻虾仁 committed
Nov 29, 2025 at 00:41 UTC
3bcbb30cbf19c128b97b7d452a5a201098f2cc48
1 file changed
+1
vllm/pooling_params.py
+1
@@ -220,6 +220,7 @@ class PoolingParams(
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"truncate_prompt_tokens={self.truncate_prompt_tokens}, "
224
f"extra_kwargs={self.extra_kwargs})"
225
)
226