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
Fix the typo in SamplingParams' docstring (#1886)
Jerry committed
Dec 1, 2023 at 18:06 UTC
f86bd6190ad300051fce5f0a13ba03b29e5e199a
1 file changed
+1
-1
vllm/sampling_params.py
+1
-1
@@ -69,7 +69,7 @@ class SamplingParams:
69
The returned output will not contain the stop strings.
70
stop_token_ids: List of tokens that stop the generation when they are
71
generated. The returned output will contain the stop tokens unless
72
- the stop tokens are sepcial tokens.
72
+ the stop tokens are special tokens.
73
ignore_eos: Whether to ignore the EOS token and continue generating
74
tokens after the EOS token is generated.
75
max_tokens: Maximum number of tokens to generate per output sequence.