From 370375435a9c4177a4a34144910fffe84593f1a4 Mon Sep 17 00:00:00 2001 From: Jing Xu Date: Wed, 11 Sep 2024 12:56:51 +0900 Subject: [PATCH] bug fix (#3252) --- xpu/2.3.110+xpu/tutorials/api_doc.html | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/xpu/2.3.110+xpu/tutorials/api_doc.html b/xpu/2.3.110+xpu/tutorials/api_doc.html index 190a71aa8..e3ecb9fce 100644 --- a/xpu/2.3.110+xpu/tutorials/api_doc.html +++ b/xpu/2.3.110+xpu/tutorials/api_doc.html @@ -338,7 +338,7 @@

General

Warning

-

Please invoke optimize_transformers function AFTER invoking DeepSpeed in Tensor Parallel +

Please invoke ipex.llm.optimize function AFTER invoking DeepSpeed in Tensor Parallel inference scenario.

Examples

@@ -346,7 +346,7 @@

General >>> model = ... >>> model.load_state_dict(torch.load(PATH)) >>> model.eval() ->>> optimized_model = ipex.optimize_transformers(model, dtype=torch.bfloat16) +>>> optimized_model = ipex.llm.optimize(model, dtype=torch.bfloat16) >>> optimized_model.generate() @@ -789,4 +789,4 @@

C++ API< - \ No newline at end of file +