We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 83c5df7 commit 95f8e5bCopy full SHA for 95f8e5b
tests/py/dynamo/llm/test_llm_models.py
@@ -23,15 +23,15 @@ def test_llm_decoder_layer(precision):
23
args.debug = False
24
args.num_tokens = 128
25
args.model = "Qwen/Qwen2.5-0.5B-Instruct"
26
- args.precision = precision
+ args.model_precision = precision
27
args.min_block_size = 1
28
args.prompt = "What is parallel programming ?"
29
- if args.precision == "FP16":
+ if args.model_precision == "FP16":
30
dtype = torch.float16
31
- elif args.precision == "BF16":
+ elif args.model_precision == "BF16":
32
dtype = torch.bfloat16
33
else:
34
- args.precision = "FP32"
+ args.model_precision = "FP32"
35
dtype = torch.float32
36
37
model = (
0 commit comments