File tree Expand file tree Collapse file tree 1 file changed +3
-3
lines changed Expand file tree Collapse file tree 1 file changed +3
-3
lines changed Original file line number Diff line number Diff line change 11
11
12
12
13
13
def test_compressed_tensors_w8a8_static_setup (vllm_runner ):
14
- model_path = "nm-testing/tinyllama-one-shot -static-quant-test-compressed "
14
+ model_path = "nm-testing/tinyllama-oneshot-w8a8 -static-v2 "
15
15
llm = vllm_runner (model_path ,
16
16
quantization = "compressed-tensors" ,
17
17
enforce_eager = True )
@@ -40,9 +40,9 @@ def test_compressed_tensors_w8a8_static_setup(vllm_runner):
40
40
41
41
42
42
def test_compressed_tensors_w8a8_dynanmic_per_token (vllm_runner ):
43
- model_path = "nm-testing/tinyllama-one-shot -dynamic-test "
43
+ model_path = "nm-testing/tinyllama-oneshot-w8a8 -dynamic-token-v2 "
44
44
llm = vllm_runner (model_path ,
45
- quantization = "sparseml " ,
45
+ quantization = "compressed-tensors " ,
46
46
enforce_eager = True ,
47
47
dtype = torch .float16 )
48
48
model = llm .model .llm_engine .model_executor .driver_worker .model_runner .model
You can’t perform that action at this time.
0 commit comments