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, 01:45 UTC
[Misc] fix typo in block manager (#4453)
Pastel! committed
May 1, 2024 at 11:41 UTC
a822eb3413087062a38cea495564ec4a7093c3e5
1 file changed
+1
-1
vllm/core/block_manager_v1.py
+1
-1
@@ -391,7 +391,7 @@ class BlockSpaceManagerV1(BlockSpaceManager):
391
block_table.append(block_table[len(block_table) %
392
self.block_sliding_window])
393
else:
394
- # The sequence has a new logical block.
394
+ # The sequence hash a new logical block.
395
# Allocate a new physical block.
396
new_block = self._allocate_last_physical_block(seq)
397
block_table.append(new_block)