Delete cutlass_mla, non-Marlin GPTQ, AWQ AOT kernel, and Dual Chunk Flash Attention (#32114)

Co-authored-by: Brayden Zhong <brayden@radixark.ai>
This commit is contained in:
Brayden Zhong
2026-09-10 15:12:01 +08:00
committed by GitHub
co-authored by Brayden Zhong
parent 7152c14384
commit c0b790cf7f
71 changed files with 48 additions and 12654 deletions
@@ -11,13 +11,6 @@ from sglang.test.ci.ci_register import register_cuda_ci
register_cuda_ci(est_time=9, stage="base-b-kernel-unit", runner_config="1-gpu-large")
try:
from sgl_kernel import awq_dequantize as aot_awq_dequantize
AOT_AVAILABLE = True
except ImportError:
AOT_AVAILABLE = False
def reverse_awq_order(t: torch.Tensor):
bits = 4
@@ -117,54 +110,5 @@ def test_awq_dequantize_jit_vs_torch(
)
@pytest.mark.parametrize(
"qweight_row,qweight_col,is_bf16_act",
list(
itertools.product(
[128, 256, 512, 1024, 3584],
[16, 32, 64, 128, 448],
[True, False],
)
),
)
def test_awq_dequantize_jit_vs_aot(
qweight_row: int, qweight_col: int, is_bf16_act: bool
):
if not AOT_AVAILABLE:
pytest.skip("sgl_kernel AOT not available")
device = torch.device("cuda")
qweight = torch.randint(
0,
torch.iinfo(torch.int32).max,
(qweight_row, qweight_col),
dtype=torch.int32,
device=device,
)
group_size = qweight_row
scales_row = qweight_row // group_size
scales_col = qweight_col * 8
if is_bf16_act:
scales = torch.rand(scales_row, scales_col, dtype=torch.bfloat16, device=device)
else:
scales = torch.rand(scales_row, scales_col, dtype=torch.float16, device=device)
qzeros = torch.randint(
0,
torch.iinfo(torch.int32).max,
(scales_row, qweight_col),
dtype=torch.int32,
device=device,
)
# Run both implementations
aot_out = aot_awq_dequantize(qweight, scales, qzeros)
jit_out = jit_awq_dequantize(qweight, scales, qzeros)
# Bitwise equality
torch.testing.assert_close(jit_out, aot_out, rtol=0, atol=0)
if __name__ == "__main__":
sys.exit(pytest.main([__file__, "-v", "-s"]))