A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 21:00 UTC
Temporarily disable test_awq_gemm_opcheck (#14251)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Mar 5, 2025 at 01:10 UTC
dae9ec464cc762758e5c195d2a1ddef1abedfcf7
1 file changed
+1
tests/kernels/test_awq.py
+1
@@ -26,6 +26,7 @@ def test_awq_dequantize_opcheck():
26
(qweight, scales, zeros, split_k_iters, thx, thy))
27
28
29
+@pytest.mark.skip(reason="Not working; needs investigation.")
30
@pytest.mark.skipif(not hasattr(torch.ops._C, "awq_gemm"),
31
reason="AWQ is not supported on this GPU type.")
32
def test_awq_gemm_opcheck():