biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[AMD][torch.compile] Enable silu+fp8_quant fusion for rocm (#18082)

Browse Source 
Signed-off-by: charlifu <charlifu@amd.com>
This commit is contained in:
Charlie Fu
2025-05-14 00:13:56 -05:00
committed by GitHub
parent 2d912fb66f
commit 7b2f28deba
6 changed files with 14 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/kernels/quantization/test_rocm_skinny_gemms.py
View File

@@ -58,8 +58,9 @@ def test_rocm_wvsplitk_kernel(n, k, m, dtype, seed):
@pytest.mark.parametrize("m", M + [28672]) # m >= 16
@pytest.mark.parametrize("dtype", DTYPES)
@pytest.mark.parametrize("seed", SEEDS)
@pytest.mark.skipif(not current_platform.is_rocm(),
reason="only test for rocm")
@pytest.mark.skipif(
not (current_platform.is_rocm() and current_platform.supports_fp8()),
reason="only test for rocm fp8")
def test_rocm_wvsplitk_fp8_kernel(n, k, m, dtype, seed):
torch.manual_seed(seed)