@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / a132435204
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

Fix typo (#1383)

Wang Ran (汪然) committed Oct 17, 2023 at 12:53 UTC a132435204aac8506e41813f90d08ddf7eca43b2
1 file changed +3 -3
vllm/model_executor/input_metadata.py
+3 -3
@@ -79,7 +79,7 @@ class InputMetadata:
79 f'prompt_lens={self.prompt_lens}, '
80 f'num_generation_tokens={self.num_generation_tokens}, '
81 f'context_lens={self.context_lens}, '
82 - f'max_context_len={self.max_context_len}), '
82 + f'max_context_len={self.max_context_len}, '
83 f'max_num_blocks_per_seq={self.max_num_blocks_per_seq}, '
84 - f'block_tables={self.block_tables}), '
85 - f'slot_mapping={self.slot_mapping}')
84 + f'block_tables={self.block_tables}, '
85 + f'slot_mapping={self.slot_mapping})')