[Perf][NPU] Enable native GQA & fused AddNorm for MiniMax-H3 encoder (#6040)
Signed-off-by: MarkPoloChina <1228479724@qq.com> Signed-off-by: XiongZhongwei <1228479724@qq.com>
This commit is contained in:
1 parent
a708ae5b7a
commit
40dcfdbb43
11 files changed
+520
-28
No files matched your search
@@ -964,6 +964,80 @@ def test_minimax_h3_advertises_the_official_ref2va_image_limit():
|
||||
assert get_diffusion_model_metadata("MiniMaxH3Pipeline").max_multimodal_image_inputs == 9
|
||||
|
||||
|
||||
def test_text_attention_routes_local_gqa_heads_through_sdpa_helper(monkeypatch):
|
||||
from vllm_omni.diffusion.models.minimax_h3 import encoder as encoder_module
|
||||
|
||||
class FakeEncoderGroup:
|
||||
rank_in_group = 0
|
||||
world_size = 2
|
||||
|
||||
def all_reduce(self, tensor):
|
||||
del tensor
|
||||
|
||||
config = SimpleNamespace(
|
||||
hidden_size=8,
|
||||
num_attention_heads=4,
|
||||
num_key_value_heads=2,
|
||||
head_dim=2,
|
||||
rms_norm_eps=1e-6,
|
||||
)
|
||||
with (
|
||||
patch("vllm.model_executor.parameter.get_tensor_model_parallel_rank", return_value=0),
|
||||
patch("vllm.model_executor.parameter.get_tensor_model_parallel_world_size", return_value=1),
|
||||
):
|
||||
attention = encoder_module.MiniMaxH3Qwen3VLTextAttention(FakeEncoderGroup(), config, torch.float32)
|
||||
# This CPU contract test only needs projection shapes and head reshaping.
|
||||
# Avoid dispatching platform-specific norm and linear kernels (for example,
|
||||
# rocm_unquantized_gemm when the test suite is collected on ROCm).
|
||||
attention.q_norm = nn.Identity()
|
||||
attention.k_norm = nn.Identity()
|
||||
with torch.no_grad():
|
||||
attention.qkv_proj.weight.zero_()
|
||||
attention.o_proj = nn.Linear(
|
||||
attention.qkv_proj.local_num_heads * attention.head_dim,
|
||||
config.hidden_size,
|
||||
bias=False,
|
||||
)
|
||||
attn_call = {}
|
||||
|
||||
def fake_attention(query, key, value):
|
||||
attn_call.update(query_shape=query.shape, key_shape=key.shape, value_shape=value.shape)
|
||||
return query
|
||||
|
||||
monkeypatch.setattr(encoder_module, "_scaled_dot_product_attention", fake_attention)
|
||||
hidden_states = torch.randn(1, 3, config.hidden_size)
|
||||
cos = torch.ones(1, 3, config.head_dim)
|
||||
sin = torch.zeros_like(cos)
|
||||
|
||||
output = attention(hidden_states, (cos, sin))
|
||||
|
||||
assert attn_call["query_shape"] == (1, config.num_attention_heads // 2, 3, config.head_dim)
|
||||
assert attn_call["key_shape"] == (1, config.num_key_value_heads // 2, 3, config.head_dim)
|
||||
assert attn_call["value_shape"] == (1, config.num_key_value_heads // 2, 3, config.head_dim)
|
||||
assert output.shape == hidden_states.shape
|
||||
|
||||
|
||||
def test_text_attention_sdpa_helper_preserves_expanded_kv_fallback(monkeypatch):
|
||||
from vllm_omni.diffusion.models.minimax_h3 import encoder as encoder_module
|
||||
|
||||
sdpa_call = {}
|
||||
|
||||
def fake_sdpa(query, key, value, **kwargs):
|
||||
sdpa_call.update(query_shape=query.shape, key_shape=key.shape, value_shape=value.shape, kwargs=kwargs)
|
||||
return query
|
||||
|
||||
monkeypatch.setattr(torch.nn.functional, "scaled_dot_product_attention", fake_sdpa)
|
||||
output = encoder_module._scaled_dot_product_attention(
|
||||
torch.randn(1, 4, 3, 8),
|
||||
torch.randn(1, 2, 3, 8),
|
||||
torch.randn(1, 2, 3, 8),
|
||||
)
|
||||
|
||||
assert sdpa_call["query_shape"] == sdpa_call["key_shape"] == sdpa_call["value_shape"] == (1, 4, 3, 8)
|
||||
assert sdpa_call["kwargs"] == {"dropout_p": 0.0, "is_causal": True}
|
||||
assert output.shape == (1, 4, 3, 8)
|
||||
|
||||
|
||||
def test_encoder_forward_uses_hook_compatible_encode_entrypoint():
|
||||
from vllm_omni.diffusion.models.minimax_h3.encoder import (
|
||||
MiniMaxH3Qwen3VLEncoder,
|
||||
|
||||
Reference in new issue
Block a user