[Attention] Minor refactor: layer takes ownership of the MLA prefill backend (#41744)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-05-05 23:22:41 +00:00
committed by GitHub
parent 8c57b6e7bc
commit 01b9b5af67
7 changed files with 74 additions and 150 deletions
@@ -238,9 +238,6 @@ from vllm.model_executor.layers.quantization.utils.quant_utils import (
kFp8StaticTensorSym,
kNvfp4Dynamic,
)
from vllm.model_executor.layers.rotary_embedding.deepseek_scaling_rope import (
yarn_get_mscale,
)
from vllm.platforms import current_platform
from vllm.utils.flashinfer import has_flashinfer
from vllm.utils.math_utils import cdiv, round_down
@@ -262,7 +259,10 @@ from vllm.v1.attention.backend import (
MLAAttentionImpl,
SparseMLAAttentionImpl,
)
from vllm.v1.attention.backends.mla.prefill import MLAPrefillBackend
from vllm.v1.attention.backends.mla.prefill import (
MLAPrefillBackend,
get_mla_prefill_backend,
)
from vllm.v1.attention.backends.utils import (
get_dcp_local_seq_lens,
split_decodes_and_prefills,
@@ -454,20 +454,32 @@ class MLAAttention(nn.Module, AttentionLayerBase):
self.q_pad_num_heads = getattr(self.impl, "q_pad_num_heads", None)
self.use_direct_call = not current_platform.opaque_attention_op()
compilation_config = get_current_vllm_config().compilation_config
vllm_config = get_current_vllm_config()
compilation_config = vllm_config.compilation_config
if prefix in compilation_config.static_forward_context:
raise ValueError(f"Duplicate layer name: {prefix}")
compilation_config.static_forward_context[prefix] = self
prefill_backend_cls = get_mla_prefill_backend(vllm_config)
self.prefill_backend = prefill_backend_cls(
num_heads=self.num_heads,
scale=self.scale,
kv_lora_rank=self.kv_lora_rank,
qk_nope_head_dim=self.qk_nope_head_dim,
qk_rope_head_dim=self.qk_rope_head_dim,
v_head_dim=self.v_head_dim,
vllm_config=vllm_config,
)
self.kv_cache = torch.tensor([])
self.use_sparse = use_sparse
vllm_config = get_current_vllm_config_or_none()
_vllm_config = get_current_vllm_config_or_none()
self.dcp_a2a = (
vllm_config is not None
and vllm_config.parallel_config.decode_context_parallel_size > 1
and vllm_config.parallel_config.dcp_comm_backend == "a2a"
_vllm_config is not None
and _vllm_config.parallel_config.decode_context_parallel_size > 1
and _vllm_config.parallel_config.dcp_comm_backend == "a2a"
)
# Initialize q/k/v range constants.
@@ -1330,35 +1342,6 @@ def get_mla_dims(model_config: ModelConfig) -> MLADims:
)
def get_mla_prefill_scale(model_config: ModelConfig) -> float:
hf_text_config = model_config.hf_text_config
mla_dims = get_mla_dims(model_config)
qk_head_dim = mla_dims.qk_nope_head_dim + mla_dims.qk_rope_head_dim
scale = qk_head_dim**-0.5
# Deepseek V4 disables YaRN mscale for attention; Deepseek V2/V3 applies
# the same mscale correction when constructing the MLA attention module.
if hasattr(hf_text_config, "compress_ratios"):
return scale
rope_parameters = getattr(hf_text_config, "rope_parameters", None)
if rope_parameters is None:
rope_parameters = getattr(hf_text_config, "rope_scaling", None)
if rope_parameters is None:
return scale
rope_type = rope_parameters.get("rope_type", rope_parameters.get("type"))
apply_yarn_scaling = rope_parameters.get("apply_yarn_scaling", True)
if rope_type != "default" and apply_yarn_scaling:
mscale_all_dim = rope_parameters.get("mscale_all_dim", False)
scaling_factor = rope_parameters["factor"]
mscale = yarn_get_mscale(float(scaling_factor), float(mscale_all_dim))
scale *= mscale * mscale
return scale
@functools.cache
def backend_supports_prefill_query_quantization() -> bool:
"""Check if the selected MLA prefill backend supports query quantization.
@@ -1554,20 +1537,9 @@ class MLACommonMetadataBuilder(AttentionMetadataBuilder[M]):
device=device,
)
from vllm.v1.attention.backends.mla.prefill import get_mla_prefill_backend
prefill_backend_cls = get_mla_prefill_backend(vllm_config)
self._prefill_backend = prefill_backend_cls(
num_heads=self.num_heads,
scale=get_mla_prefill_scale(self.model_config),
kv_lora_rank=self.mla_dims.kv_lora_rank,
qk_nope_head_dim=self.mla_dims.qk_nope_head_dim,
qk_rope_head_dim=self.mla_dims.qk_rope_head_dim,
v_head_dim=self.mla_dims.v_head_dim,
vllm_config=vllm_config,
device=device,
layer_names=layer_names,
)
self._prefill_backend = self.compilation_config.static_forward_context[
layer_names[0]
].prefill_backend
supports_spec_decode = self.query_len_support != QueryLenSupport.SINGLE_ONLY
self._init_reorder_batch_threshold(