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 17, 06:45 UTC
Add stop_token_ids in SamplingParams.__repr__ (#1745)
陈序 committed
Nov 22, 2023 at 12:13 UTC
094f716bf2cdc213f2b812dbb489fbf6f4a4423c
1 file changed
+1
vllm/sampling_params.py
+1
@@ -241,6 +241,7 @@ class SamplingParams:
241
f"length_penalty={self.length_penalty}, "
242
f"early_stopping={self.early_stopping}, "
243
f"stop={self.stop}, "
244
+ f"stop_token_ids={self.stop_token_ids}, "
245
f"ignore_eos={self.ignore_eos}, "
246
f"max_tokens={self.max_tokens}, "
247
f"logprobs={self.logprobs}, "