Skip to content

Commit aec7c82

Browse files
committed
update model names
1 parent fb1b863 commit aec7c82

File tree

1 file changed

+3
-3
lines changed

1 file changed

+3
-3
lines changed

tests/quantization/test_compressed_tensors.py

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@
1111

1212

1313
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"
1515
llm = vllm_runner(model_path,
1616
quantization="compressed-tensors",
1717
enforce_eager=True)
@@ -40,9 +40,9 @@ def test_compressed_tensors_w8a8_static_setup(vllm_runner):
4040

4141

4242
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"
4444
llm = vllm_runner(model_path,
45-
quantization="sparseml",
45+
quantization="compressed-tensors",
4646
enforce_eager=True,
4747
dtype=torch.float16)
4848
model = llm.model.llm_engine.model_executor.driver_worker.model_runner.model

0 commit comments

Comments
 (0)