@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 094f716bf2
Fork 0

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}, "