ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

[NPU] Hot fix of load_low_bit (#12344)

Browse source
This commit is contained in:
binbin Deng 2024-11-06 10:07:00 +08:00 committed by GitHub
parent 899a30331a
commit 69e3a56943
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
python/llm/src/ipex_llm/transformers/npu_model.py
View file

@ -549,7 +549,7 @@ class _BaseAutoModelClass:
from ipex_llm.transformers.npu_models.convert_mp import optimize_llm from ipex_llm.transformers.npu_models.convert_mp import optimize_llm
optimize_llm( optimize_llm(
llm, llm,
max_output_len=max_context_len, max_context_len=max_context_len,
max_prompt_len=max_prompt_len, max_prompt_len=max_prompt_len,
inter_pp=inter_pp, inter_pp=inter_pp,
intra_pp=intra_pp, intra_pp=intra_pp,