biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Re-enable the 80 char line width limit (#3305)

Browse Source
This commit is contained in:
Zhuohan Li
2024-03-10 19:49:14 -07:00
committed by GitHub
parent 4b59f00e91
commit 2f8844ba08
67 changed files with 557 additions and 528 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/sampling_params.py
View File

@@ -74,8 +74,8 @@ class SamplingParams:
stop_token_ids: List of tokens that stop the generation when they are
generated. The returned output will contain the stop tokens unless
the stop tokens are special tokens.
include_stop_str_in_output: Whether to include the stop strings in output
text. Defaults to False.
include_stop_str_in_output: Whether to include the stop strings in
output text. Defaults to False.
ignore_eos: Whether to ignore the EOS token and continue generating
tokens after the EOS token is generated.
max_tokens: Maximum number of tokens to generate per output sequence.