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

[NPU] Update qwen2 compile config (#12383)

Browse source 
* update

* fix
This commit is contained in:
Ruonan Wang 2024-11-12 16:59:44 +08:00 committed by GitHub
parent 7a97fbb779
commit 6bf5a8c230
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_models/qwen2_mp.py
View file

@ -234,7 +234,7 @@ class LowBitQwenMultiDecoderlayer(LLMBaseNNFactory):
print(f"{mode} start compiling") print(f"{mode} start compiling")
if ( if (
group_size != 0 group_size != 0
and (mode == "prefill" or num_layers == 2) and (mode == "prefill" or num_layers == 2 or num_layers == 3)
and os.environ.get("IPEX_LLM_NPU_DISABLE_COMPILE_OPT", "0") != "1" and os.environ.get("IPEX_LLM_NPU_DISABLE_COMPILE_OPT", "0") != "1"
): ):
self.compile(npu_dpu_groups=6) self.compile(npu_dpu_groups=6)