alihan/llm-text-generation-inference
1
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2023-08-15 01:09:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix(server): fix flash causal (#219)

Browse Source
This commit is contained in:
OlivierDehaene
2023-04-21 19:49:08 +02:00
committed by GitHub
parent 86bca365df
commit 1ffea36ec2
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/models/flash_causal_lm.py
View File

@@ -225,6 +225,7 @@ class FlashCausalLMBatch(Batch):
return FlashCausalLMBatch(
batch_id=self.batch_id,
past_pad=self.past_pad,
requests=requests,
requests_idx_mapping=requests_idx_mapping,
input_ids=input_ids,
@@ -311,6 +312,7 @@ class FlashCausalLMBatch(Batch):
return FlashCausalLMBatch(
batch_id=batches[0].batch_id,
past_pad=batches[0].past_pad,
requests=requests,
requests_idx_mapping=requests_idx_mapping,
input_ids=input_ids,