huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-23 16:02:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix to non-LLAMA models (#177)

Browse Source 
Co-authored-by: Jacek Czaja <jczaja@habana.ai>
This commit is contained in:
Jacek Czaja 2024-07-04 13:42:24 +02:00 committed by GitHub
parent 6168aa4100
commit 5df20f88ff
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
server/text_generation_server/models/causal_lm.py
View File

@ -850,9 +850,12 @@ class CausalLM(Model):
"attention_mask": attention_mask,
"past_key_values": past_key_values,
"token_idx": token_idx,
"lazy_mode": LAZY_MODE == 1,
}
# Optimum Habana got "lazy_mode" key-val only supported for llama type of models
if self.model.config.model_type == "llama" :
kwargs["lazy_mode"] = LAZY_MODE == 1
if self.has_position_ids:
kwargs["position_ids"] = position_ids