huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

update comment

Browse Source
This commit is contained in:
Cyril Vallez 2025-01-20 15:25:10 +01:00
parent 6e0f37c0ca
commit 52afdcc281
No known key found for this signature in database
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
server/text_generation_server/models/transformers_flash_causal_lm.py
View File

@ -243,10 +243,8 @@ class TransformersFlashCausalLM(FlashCausalLM):
adapter_data=None, # not supported, but passed to match original signature adapter_data=None, # not supported, but passed to match original signature
): ):
hidden_states = self.model.model.forward( hidden_states = self.model.model.forward(
input_ids=input_ids.unsqueeze(0), # expand dim to easily fit transformers input_ids=input_ids.unsqueeze(0), # expand dim to fit Transformers
position_ids=position_ids.unsqueeze( position_ids=position_ids.unsqueeze(0), # expand dim to fit Transformers
0
), # expand dim to easily fit transformers
past_key_values=None, # we use self.kv_cache instead of transformers cache object past_key_values=None, # we use self.kv_cache instead of transformers cache object
use_cache=False, # we use self.kv_cache instead of transformers cache object use_cache=False, # we use self.kv_cache instead of transformers cache object
return_dict=True, return_dict=True,