From 7b0629dac45d472e5d96953a4772fda4aacdd94b Mon Sep 17 00:00:00 2001
From: zhouwei <363232733@qq.com>
Date: Mon, 6 May 2024 13:29:59 +0800
Subject: [PATCH] The training efficiency of the Ascend 910A has been
 significantly enhanced, leveraging the full computational power of the NPU
 (Neural Processing Unit) and the capabilities of torch_npu, a PyTorch library
 optimized for NPUs. This improvement has resulted in a remarkable tenfold
 increase in efficiency.

Former-commit-id: 28ae947161d4670d4f865cbaad84397d47215a53
---
 src/train.py | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/src/train.py b/src/train.py
index 6a3212cb..e2609b66 100644
--- a/src/train.py
+++ b/src/train.py
@@ -1,3 +1,7 @@
+import os
+import torch
+import torch_npu
+from torch_npu.contrib import transfer_to_npu
 from llmtuner.train.tuner import run_exp
 
 
@@ -11,4 +15,6 @@ def _mp_fn(index):
 
 
 if __name__ == "__main__":
+    use_jit_compile = os.getenv('JIT_COMPILE', 'False').lower() in ['true', '1']
+    torch.npu.set_compile_mode(jit_compile=use_jit_compile)
     main()