[Bugfix] [ROCm] [DSV4] [Perf] Add aiter mhc support (#41946)

Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
This commit is contained in:
TJian
2026-05-13 21:43:15 +08:00
committed by GitHub
co-authored by Yongye Zhu
parent 0ddaf6dffa
commit a8887c208f
12 changed files with 1929 additions and 1042 deletions
+58 -2
View File
@@ -3,7 +3,7 @@
import pytest
import torch
import vllm.model_executor.layers.mhc as mhc_ops # noqa: F401
import vllm.model_executor.kernels.mhc # noqa: F401
from vllm.platforms import current_platform
from vllm.utils.torch_utils import set_random_seed
@@ -74,6 +74,23 @@ def mhc_post_ref(
return (x.float().unsqueeze(-2) * post_layer_mix + term2).bfloat16()
def hc_head_ref(
residual: torch.Tensor,
fn: torch.Tensor,
hc_scale: torch.Tensor,
hc_base: torch.Tensor,
rms_eps: float,
hc_eps: float,
) -> torch.Tensor:
residual_flat = residual.flatten(-2).float()
residual_norm = residual_flat * torch.rsqrt(
residual_flat.square().mean(dim=-1, keepdim=True) + rms_eps
)
pre_mix = torch.nn.functional.linear(residual_norm, fn)
pre_mix = torch.sigmoid(pre_mix * hc_scale + hc_base) + hc_eps
return torch.sum(pre_mix.unsqueeze(-1) * residual.float(), dim=-2).bfloat16()
@pytest.mark.skipif(
not current_platform.is_cuda(),
reason="CUDA required",
@@ -121,7 +138,7 @@ def test_mhc_fused_post_pre(num_tokens, hidden_size, hc_mult):
residual_ref, post_mix_ref, res_mix_ref, layer_input_ref = run_ref()
residual, post_mix, res_mix, x = torch.ops.vllm.mhc_fused_post_pre(
residual, post_mix, res_mix, x = torch.ops.vllm.mhc_fused_post_pre_tilelang(
x,
residual,
post_layer_mix,
@@ -140,3 +157,42 @@ def test_mhc_fused_post_pre(num_tokens, hidden_size, hc_mult):
torch.testing.assert_close(post_mix, post_mix_ref, atol=1e-2, rtol=1e-2)
torch.testing.assert_close(res_mix, res_mix_ref, atol=1e-2, rtol=1e-2)
torch.testing.assert_close(x, layer_input_ref, atol=1e-2, rtol=1e-2)
@pytest.mark.skipif(
not current_platform.is_rocm(),
reason="ROCm required",
)
@pytest.mark.parametrize("num_tokens", [1, 4, 8, 128])
@pytest.mark.parametrize("hidden_size", [4096, 7168])
@pytest.mark.parametrize("hc_mult", [4])
def test_hc_head_triton(num_tokens, hidden_size, hc_mult):
torch.set_default_device(DEVICE)
set_random_seed(0)
residual = torch.randn((num_tokens, hc_mult, hidden_size), dtype=torch.bfloat16)
fn = torch.randn((hc_mult, hc_mult * hidden_size), dtype=torch.float32) * 1e-4
hc_scale = torch.randn((1,), dtype=torch.float32) * 0.1
hc_base = torch.randn((hc_mult,), dtype=torch.float32) * 0.1
rms_eps = hc_eps = 1e-6
out = torch.empty((num_tokens, hidden_size), dtype=torch.bfloat16)
out.fill_(float("nan"))
result = torch.ops.vllm.hc_head_triton(
residual,
fn,
hc_scale,
hc_base,
out,
hidden_size,
rms_eps,
hc_eps,
hc_mult,
)
assert result is None
assert not torch.isnan(out).any()
out_ref = hc_head_ref(residual, fn, hc_scale, hc_base, rms_eps, hc_eps)
torch.testing.assert_close(out, out_ref, atol=5e-2, rtol=1e-2)