huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix

Browse Source
This commit is contained in:
OlivierDehaene 2023-06-30 16:47:00 +02:00
parent c52e84fe10
commit 8ec0edcfe3
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
server/text_generation_server/models/flash_causal_lm.py
View File

@ -94,6 +94,7 @@ class CacheManager:
slots.append(allocated_slots)
block_tables.append(allocated_blocks.tolist())
block_tables_tensor[i, :needed_blocks] = allocated_blocks
cumulative_blocks += needed_blocks
batch.needed_blocks_slots = None
batch.block_tables = block_tables