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 drop

Browse Source
This commit is contained in:
OlivierDehaene 2023-06-30 16:52:25 +02:00
parent 8ec0edcfe3
commit 3c4243d627
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/text_generation_server/models/flash_causal_lm.py
View File

@ -640,6 +640,10 @@ class FlashCausalLMBatch(Batch):
device=batches[0].next_token_chooser.device, device=batches[0].next_token_chooser.device,
) )
# Needed to avoid dropping blocks when the batches will go out of scope
for b in batches:
b.block_tables = None
return FlashCausalLMBatch( return FlashCausalLMBatch(
batch_id=batches[0].batch_id, batch_id=batches[0].batch_id,
requests=requests, requests=requests,