Module neuralops.attentions.qcqa_attention

Quality and Capacity-Aware Grouped Query Attention (QCQA) — v2.

Dynamically synthesizes head-specific key-value representations for each query head via continuous learned routing distributions over a compressed set of KV heads.

Functions

def inject_qcqa(layer: Any = None,
model: Any = None,
model_config: Any = None,
comp_config: Any = None,
layer_idx: int = 0,
total_layers: int = 12,
old_attn: nn.Module | None = None,
target_layer_idx: int | None = None,
**kwargs: Any)

Expand source code

@ATTENTION_REGISTRY.register("qcqa_inject")
@ATTENTION_REGISTRY.register("inject_qcqa")
def inject_qcqa(
    layer: Any = None,
    model: Any = None,
    model_config: Any = None,
    comp_config: Any = None,
    layer_idx: int = 0,
    total_layers: int = 12,
    old_attn: nn.Module | None = None,
    target_layer_idx: int | None = None,
    _depth: int = 0,
    **kwargs: Any,
):
    if _depth > 8:
        logger.warning("inject_qcqa: max recursion depth exceeded, aborting.")
        return None

    target = layer if layer is not None else model
    if target is None:
        target = kwargs.get("model", kwargs.get("layer"))
    if target is None:
        return None

    cfg = model_config if model_config is not None else getattr(target, "config", None)

    layer_list = None
    if hasattr(target, "distilbert") and hasattr(target.distilbert, "transformer"):
        layer_list = target.distilbert.transformer.layer
    elif hasattr(target, "roberta") and hasattr(target.roberta, "encoder"):
        layer_list = target.roberta.encoder.layer
    elif hasattr(target, "transformer") and hasattr(target.transformer, "h"):
        layer_list = target.transformer.h
    elif hasattr(target, "h") and isinstance(target.h, (torch.nn.ModuleList, list)):
        layer_list = target.h
    elif hasattr(target, "model") and hasattr(target.model, "layers"):
        layer_list = target.model.layers
    elif hasattr(target, "encoder") and hasattr(target.encoder, "layer"):
        layer_list = target.encoder.layer
    elif (
        hasattr(target, "bert")
        and hasattr(target.bert, "encoder")
        and hasattr(target.bert.encoder, "layer")
    ):
        layer_list = target.bert.encoder.layer
    elif hasattr(target, "layers") and isinstance(target.layers, (torch.nn.ModuleList, list)):
        layer_list = target.layers

    if layer_list is not None:
        num_injected = 0
        tot = len(layer_list)
        for idx, lyr in enumerate(layer_list):
            res = inject_qcqa(
                layer=lyr,
                model_config=cfg,
                comp_config=comp_config,
                layer_idx=idx,
                total_layers=tot,
                _depth=_depth + 1,
                **kwargs,
            )
            if res is not None:
                num_injected += 1
        return target if num_injected > 0 else None

    try:

        def _already_injected(m):
            if m is None:
                return False
            if isinstance(m, QCQAAttention):
                return True
            if "QCQA" in m.__class__.__name__:
                return True
            inner = getattr(m, "inner", None)
            if isinstance(inner, QCQAAttention):
                return True
            wrapped = getattr(m, "_wrapped_attention", None)
            if isinstance(wrapped, QCQAAttention):
                return True
            return False

        if _already_injected(old_attn):
            return None

        src = old_attn
        if src is None:
            for attr in ("attention", "self_attn", "attn", "self"):
                if hasattr(target, attr):
                    cand = getattr(target, attr)
                    if isinstance(cand, nn.Module) and cand is not target:
                        src = getattr(cand, "self", cand)
                        break
        if src is None:
            return None

        if _already_injected(src):
            return None

        new_attn = QCQAAttention(
            config=cfg,
            comp_config=comp_config,
            pretrained_attn=src,
            **kwargs,
        )

        if hasattr(target, "attention"):
            if hasattr(target.attention, "self"):
                target.attention.self = new_attn
                new_attn.is_nested_encoder = True
            else:
                target.attention = new_attn
            return new_attn
        for attr in ("self_attn", "attn", "self"):
            if hasattr(target, attr):
                setattr(target, attr, new_attn)
                return new_attn
        target.attention = new_attn
        return new_attn
    except Exception as e:
        logger.exception("inject_qcqa failed: %s", e)
        return None

def inject_qcqa_attention(layer: Any = None,
model: Any = None,
model_config: Any = None,
comp_config: Any = None,
layer_idx: int = 0,
total_layers: int = 12,
old_attn: nn.Module | None = None,
target_layer_idx: int | None = None,
**kwargs: Any)

Expand source code

@ATTENTION_REGISTRY.register("qcqa_inject")
@ATTENTION_REGISTRY.register("inject_qcqa")
def inject_qcqa(
    layer: Any = None,
    model: Any = None,
    model_config: Any = None,
    comp_config: Any = None,
    layer_idx: int = 0,
    total_layers: int = 12,
    old_attn: nn.Module | None = None,
    target_layer_idx: int | None = None,
    _depth: int = 0,
    **kwargs: Any,
):
    if _depth > 8:
        logger.warning("inject_qcqa: max recursion depth exceeded, aborting.")
        return None

    target = layer if layer is not None else model
    if target is None:
        target = kwargs.get("model", kwargs.get("layer"))
    if target is None:
        return None

    cfg = model_config if model_config is not None else getattr(target, "config", None)

    layer_list = None
    if hasattr(target, "distilbert") and hasattr(target.distilbert, "transformer"):
        layer_list = target.distilbert.transformer.layer
    elif hasattr(target, "roberta") and hasattr(target.roberta, "encoder"):
        layer_list = target.roberta.encoder.layer
    elif hasattr(target, "transformer") and hasattr(target.transformer, "h"):
        layer_list = target.transformer.h
    elif hasattr(target, "h") and isinstance(target.h, (torch.nn.ModuleList, list)):
        layer_list = target.h
    elif hasattr(target, "model") and hasattr(target.model, "layers"):
        layer_list = target.model.layers
    elif hasattr(target, "encoder") and hasattr(target.encoder, "layer"):
        layer_list = target.encoder.layer
    elif (
        hasattr(target, "bert")
        and hasattr(target.bert, "encoder")
        and hasattr(target.bert.encoder, "layer")
    ):
        layer_list = target.bert.encoder.layer
    elif hasattr(target, "layers") and isinstance(target.layers, (torch.nn.ModuleList, list)):
        layer_list = target.layers

    if layer_list is not None:
        num_injected = 0
        tot = len(layer_list)
        for idx, lyr in enumerate(layer_list):
            res = inject_qcqa(
                layer=lyr,
                model_config=cfg,
                comp_config=comp_config,
                layer_idx=idx,
                total_layers=tot,
                _depth=_depth + 1,
                **kwargs,
            )
            if res is not None:
                num_injected += 1
        return target if num_injected > 0 else None

    try:

        def _already_injected(m):
            if m is None:
                return False
            if isinstance(m, QCQAAttention):
                return True
            if "QCQA" in m.__class__.__name__:
                return True
            inner = getattr(m, "inner", None)
            if isinstance(inner, QCQAAttention):
                return True
            wrapped = getattr(m, "_wrapped_attention", None)
            if isinstance(wrapped, QCQAAttention):
                return True
            return False

        if _already_injected(old_attn):
            return None

        src = old_attn
        if src is None:
            for attr in ("attention", "self_attn", "attn", "self"):
                if hasattr(target, attr):
                    cand = getattr(target, attr)
                    if isinstance(cand, nn.Module) and cand is not target:
                        src = getattr(cand, "self", cand)
                        break
        if src is None:
            return None

        if _already_injected(src):
            return None

        new_attn = QCQAAttention(
            config=cfg,
            comp_config=comp_config,
            pretrained_attn=src,
            **kwargs,
        )

        if hasattr(target, "attention"):
            if hasattr(target.attention, "self"):
                target.attention.self = new_attn
                new_attn.is_nested_encoder = True
            else:
                target.attention = new_attn
            return new_attn
        for attr in ("self_attn", "attn", "self"):
            if hasattr(target, attr):
                setattr(target, attr, new_attn)
                return new_attn
        target.attention = new_attn
        return new_attn
    except Exception as e:
        logger.exception("inject_qcqa failed: %s", e)
        return None

Classes

class LoRALinear (in_features: int,
out_features: int,
bias: bool = True,
lora_rank: int = 16,
lora_alpha: float = 32.0,
freeze_base: bool = False,
device: torch.device | None = None,
dtype: torch.dtype | None = None)

Expand source code

class LoRALinear(nn.Module):
    def __init__(
        self,
        in_features: int,
        out_features: int,
        bias: bool = True,
        lora_rank: int = 16,
        lora_alpha: float = 32.0,
        freeze_base: bool = False,
        device: torch.device | None = None,
        dtype: torch.dtype | None = None,
    ) -> None:
        super().__init__()
        factory_kwargs = {"device": device, "dtype": dtype}
        self.in_features = in_features
        self.out_features = out_features
        self.lora_rank = lora_rank
        self.lora_alpha = lora_alpha
        self.lora_scaling = (lora_alpha / lora_rank) if lora_rank > 0 else 1.0
        self.freeze_base = freeze_base

        self.weight = nn.Parameter(torch.empty((out_features, in_features), **factory_kwargs))
        if bias:
            self.bias = nn.Parameter(torch.empty(out_features, **factory_kwargs))
        else:
            self.register_parameter("bias", None)

        if self.lora_rank > 0:
            self.lora_A = nn.Parameter(torch.empty((lora_rank, in_features), **factory_kwargs))
            self.lora_B = nn.Parameter(torch.empty((out_features, lora_rank), **factory_kwargs))
        else:
            self.register_parameter("lora_A", None)
            self.register_parameter("lora_B", None)

        self.reset_parameters()
        if freeze_base:
            self.freeze_base_weights()

    def reset_parameters(self) -> None:
        nn.init.kaiming_uniform_(self.weight, a=math.sqrt(5))
        if self.bias is not None:
            fan_in, _ = nn.init._calculate_fan_in_and_fan_out(self.weight)
            bound = 1 / math.sqrt(fan_in) if fan_in > 0 else 0
            nn.init.uniform_(self.bias, -bound, bound)

        if self.lora_rank > 0 and self.lora_A is not None:
            nn.init.kaiming_uniform_(self.lora_A, a=math.sqrt(5))
            self.lora_A.requires_grad = True
        if self.lora_rank > 0 and self.lora_B is not None:
            nn.init.zeros_(self.lora_B)
            self.lora_B.requires_grad = True

    def freeze_base_weights(self) -> None:
        self.weight.requires_grad = False
        if self.bias is not None:
            self.bias.requires_grad = False
        if self.lora_rank > 0:
            if self.lora_A is not None:
                self.lora_A.requires_grad = True
            if self.lora_B is not None:
                self.lora_B.requires_grad = True

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        out = F.linear(x, self.weight, self.bias)
        if self.lora_rank > 0 and self.lora_A is not None and self.lora_B is not None:
            lora_out = F.linear(F.linear(x, self.lora_A), self.lora_B) * self.lora_scaling
            out = out + lora_out
        return out

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F


class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call :meth:to, etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Ancestors

• torch.nn.modules.module.Module

Methods

def forward(self, x: torch.Tensor) ‑> torch.Tensor

Expand source code

def forward(self, x: torch.Tensor) -> torch.Tensor:
    out = F.linear(x, self.weight, self.bias)
    if self.lora_rank > 0 and self.lora_A is not None and self.lora_B is not None:
        lora_out = F.linear(F.linear(x, self.lora_A), self.lora_B) * self.lora_scaling
        out = out + lora_out
    return out

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the :class:Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

def freeze_base_weights(self) ‑> None

Expand source code

def freeze_base_weights(self) -> None:
    self.weight.requires_grad = False
    if self.bias is not None:
        self.bias.requires_grad = False
    if self.lora_rank > 0:
        if self.lora_A is not None:
            self.lora_A.requires_grad = True
        if self.lora_B is not None:
            self.lora_B.requires_grad = True

def reset_parameters(self) ‑> None

Expand source code

def reset_parameters(self) -> None:
    nn.init.kaiming_uniform_(self.weight, a=math.sqrt(5))
    if self.bias is not None:
        fan_in, _ = nn.init._calculate_fan_in_and_fan_out(self.weight)
        bound = 1 / math.sqrt(fan_in) if fan_in > 0 else 0
        nn.init.uniform_(self.bias, -bound, bound)

    if self.lora_rank > 0 and self.lora_A is not None:
        nn.init.kaiming_uniform_(self.lora_A, a=math.sqrt(5))
        self.lora_A.requires_grad = True
    if self.lora_rank > 0 and self.lora_B is not None:
        nn.init.zeros_(self.lora_B)
        self.lora_B.requires_grad = True

class QCQAAttention (config: Any | None = None,
num_kv_heads: int | None = None,
router_temp: float = 1.0,
pretrained_attn: nn.Module | None = None,
is_decoder: bool | None = None,
**kwargs: Any)

Expand source code

@ATTENTION_REGISTRY.register("qcqa")
@ATTENTION_REGISTRY.register("qcqa_attention")
@ATTENTION_REGISTRY.register("qcqa_attn")
class QCQAAttention(BaseAttention):
    is_custom_attention: bool = True

    def __init__(
        self,
        config: Any | None = None,
        num_kv_heads: int | None = None,
        router_temp: float = 1.0,
        pretrained_attn: nn.Module | None = None,
        is_decoder: bool | None = None,
        **kwargs: Any,
    ) -> None:
        rank = kwargs.pop("rank", 64)
        super().__init__(config, rank)
        self.config = config
        comp_config = kwargs.get("comp_config") or getattr(config, "compression_config", None)

        # hidden_size detection
        h_size = (
            kwargs.get("hidden_size")
            or getattr(config, "hidden_size", None)
            or getattr(config, "d_model", None)
        )
        if h_size is None and pretrained_attn is not None:
            for cand in ("q_proj", "q_lin", "query", "c_attn"):
                mod = getattr(pretrained_attn, cand, None)
                if mod is not None and hasattr(mod, "weight"):
                    w = mod.weight
                    if w.ndim == 2:
                        if mod.__class__.__name__ == "Conv1D" or hasattr(mod, "nf"):
                            h_size = w.shape[0]
                        else:
                            h_size = w.shape[1]
                        break
        if h_size is None:
            raise ValueError("QCQAAttention: could not infer hidden_size.")
        self.dim = int(h_size)

        self.num_heads = int(
            kwargs.get("num_heads")
            or kwargs.get("num_attention_heads")
            or getattr(config, "num_attention_heads", None)
            or getattr(config, "num_heads", None)
            or 12
        )

        cfg_kv = getattr(config, "num_key_value_heads", getattr(config, "num_kv_heads", None))
        if num_kv_heads is not None:
            self.num_kv_heads = int(num_kv_heads)
        elif cfg_kv is not None:
            self.num_kv_heads = int(cfg_kv)
        else:
            self.num_kv_heads = int(kwargs.get("num_kv_heads", 4))
        self.num_kv_heads = max(1, min(self.num_kv_heads, self.num_heads))
        self.kv_repeat = max(1, self.num_heads // max(1, self.num_kv_heads))

        self.head_dim = int(
            kwargs.get("head_dim")
            or getattr(config, "head_dim", None)
            or getattr(config, "d_kv", None)
            or (self.dim // max(1, self.num_heads))
        )
        self.all_head_size = self.num_heads * self.head_dim
        self.all_kv_head_size = self.num_kv_heads * self.head_dim

        self.router_temp = float(
            _cfg_get(comp_config, "router_temp", kwargs.get("router_temp", router_temp))
        )
        if self.router_temp <= 0:
            self.router_temp = 1.0

        self.is_decoder = _detect_decoder(config, is_decoder, pretrained_attn)
        self.is_nested_encoder = False

        self.lora_rank = int(
            _cfg_get(
                config,
                "lora_rank",
                _cfg_get(comp_config, "lora_rank", kwargs.get("lora_rank", 16)),
            )
        )
        self.lora_alpha = float(
            _cfg_get(
                config,
                "lora_alpha",
                _cfg_get(comp_config, "lora_alpha", kwargs.get("lora_alpha", 32.0)),
            )
        )
        self.freeze_base = self.lora_rank > 0
        self.supports_gqa = True

        target_dtype = kwargs.get("dtype")
        if target_dtype is None and pretrained_attn is not None:
            p = next(pretrained_attn.parameters(), None)
            if p is not None:
                target_dtype = p.dtype

        self.q_proj = LoRALinear(
            self.dim,
            self.all_head_size,
            bias=True,
            lora_rank=self.lora_rank,
            lora_alpha=self.lora_alpha,
            freeze_base=self.freeze_base,
            dtype=target_dtype,
        )
        self.k_proj = LoRALinear(
            self.dim,
            self.all_kv_head_size,
            bias=True,
            lora_rank=self.lora_rank,
            lora_alpha=self.lora_alpha,
            freeze_base=self.freeze_base,
            dtype=target_dtype,
        )
        self.v_proj = LoRALinear(
            self.dim,
            self.all_kv_head_size,
            bias=True,
            lora_rank=self.lora_rank,
            lora_alpha=self.lora_alpha,
            freeze_base=self.freeze_base,
            dtype=target_dtype,
        )
        self.out_proj = LoRALinear(
            self.all_head_size,
            self.dim,
            bias=True,
            lora_rank=self.lora_rank,
            lora_alpha=self.lora_alpha,
            freeze_base=self.freeze_base,
            dtype=target_dtype,
        )

        # Aliases
        self.query = self.q_proj
        self.key = self.k_proj
        self.value = self.v_proj
        self.q_lin = self.q_proj
        self.k_lin = self.k_proj
        self.v_lin = self.v_proj
        self.out_lin = self.out_proj
        self.dense = self.out_proj
        self.o_proj = self.out_proj
        self.c_proj = self.out_proj

        # QC-FIX-20: router maps q's last dim → num_kv_heads
        self.router = nn.Linear(self.head_dim, self.num_kv_heads, bias=False)
        nn.init.normal_(self.router.weight, std=0.02)

        dropout_p = _cfg_get(
            config, "dropout", _cfg_get(config, "attention_probs_dropout_prob", 0.1)
        )
        self.dropout = nn.Dropout(dropout_p)

        source_attn = pretrained_attn if pretrained_attn is not None else kwargs.get("source_attn")
        if source_attn is not None:
            self.copy_weights(source_attn)

        if target_dtype is not None:
            self.to(target_dtype)

    # ------------------------------------------------------------------
    def copy_weights(self, src: Any) -> None:
        if src is None:
            return

        cls_name = src.__class__.__name__
        has_out_lin = hasattr(src, "out_lin") or hasattr(src, "c_proj") or hasattr(src, "o_proj")

        is_nested = False
        if (
            (
                hasattr(src, "self")
                and hasattr(src.self, "query")
                and hasattr(src, "output")
                and hasattr(src.output, "dense")
            )
            or cls_name
            in (
                "BertSelfAttention",
                "RobertaSelfAttention",
                "XLMRobertaSelfAttention",
                "ElectraSelfAttention",
            )
            or cls_name.endswith("SelfAttention")
            and "distil" not in cls_name.lower()
            and not has_out_lin
        ):
            is_nested = True
        self.is_nested_encoder = bool(is_nested)

        extracted: dict[str, tuple[torch.Tensor | None, torch.Tensor | None]] = {
            "q": (None, None),
            "k": (None, None),
            "v": (None, None),
            "o": (None, None),
        }

        if hasattr(src, "c_attn") and src.c_attn is not None:
            c_attn_mod = src.c_attn
            base_c = getattr(c_attn_mod, "base_layer", c_attn_mod)
            c_w = getattr(base_c, "weight", getattr(c_attn_mod, "weight", None))
            if c_w is not None:
                c_w = c_w.data.clone()
                if (
                    c_attn_mod.__class__.__name__ == "Conv1D"
                    or base_c.__class__.__name__ == "Conv1D"
                    or (c_w.ndim == 2 and c_w.shape[0] < c_w.shape[1])
                ):
                    c_w = c_w.t().contiguous()
                split_size = c_w.size(0) // 3
                bias_mod = getattr(base_c, "bias", getattr(c_attn_mod, "bias", None))
                c_b = bias_mod.data.clone() if bias_mod is not None else None
                extracted["q"] = (
                    c_w[:split_size, :],
                    c_b[:split_size] if c_b is not None else None,
                )
                extracted["k"] = (
                    c_w[split_size : 2 * split_size, :],
                    c_b[split_size : 2 * split_size] if c_b is not None else None,
                )
                extracted["v"] = (
                    c_w[2 * split_size :, :],
                    c_b[2 * split_size :] if c_b is not None else None,
                )

            if hasattr(src, "c_proj") and src.c_proj is not None:
                c_proj_mod = src.c_proj
                base_o = getattr(c_proj_mod, "base_layer", c_proj_mod)
                o_w = getattr(base_o, "weight", getattr(c_proj_mod, "weight", None))
                if o_w is not None:
                    o_w = o_w.data.clone()
                    if (
                        c_proj_mod.__class__.__name__ == "Conv1D"
                        or base_o.__class__.__name__ == "Conv1D"
                        or (o_w.ndim == 2 and o_w.shape[0] < o_w.shape[1])
                    ):
                        o_w = o_w.t().contiguous()
                    bias_o = getattr(base_o, "bias", getattr(c_proj_mod, "bias", None))
                    extracted["o"] = (
                        o_w,
                        bias_o.data.clone() if bias_o is not None else None,
                    )

        elif hasattr(src, "self") and hasattr(src.self, "query"):
            s = src.self
            for proj_key, sub_name in [("q", "query"), ("k", "key"), ("v", "value")]:
                mod = getattr(s, sub_name, None)
                if mod is not None and hasattr(mod, "weight"):
                    extracted[proj_key] = (
                        mod.weight.data.clone(),
                        mod.bias.data.clone() if mod.bias is not None else None,
                    )
            if hasattr(src, "output") and hasattr(src.output, "dense"):
                out_mod = src.output.dense
                extracted["o"] = (
                    out_mod.weight.data.clone(),
                    out_mod.bias.data.clone() if out_mod.bias is not None else None,
                )

        else:
            proj_candidates = {
                "q": ["q_lin", "q_proj", "query"],
                "k": ["k_lin", "k_proj", "key"],
                "v": ["v_lin", "v_proj", "value"],
                "o": ["out_lin", "out_proj", "dense", "o_proj"],
            }
            for proj_key, names in proj_candidates.items():
                for name in names:
                    if hasattr(src, name):
                        mod = getattr(src, name)
                        if mod is not None and hasattr(mod, "weight"):
                            extracted[proj_key] = (
                                mod.weight.data.clone(),
                                mod.bias.data.clone() if mod.bias is not None else None,
                            )
                            break

        missing = [
            k
            for k, (w, _) in extracted.items()
            if w is None and (k != "o" or not self.is_nested_encoder)
        ]
        if missing:
            try:
                from neuralops.core.adapters import UniversalAdapter

                adapter = UniversalAdapter()
                for k in missing:
                    w, b = adapter.get_weight_bias(src, k)
                    if w is not None:
                        extracted[k] = (w.clone(), b.clone() if b is not None else None)
            except Exception as e:
                logger.debug("UniversalAdapter fallback failed: %s", e)

        missing_after = [
            k
            for k, (w, _) in extracted.items()
            if w is None and (k != "o" or not self.is_nested_encoder)
        ]
        if missing_after:
            raise RuntimeError(
                f"QCQAAttention.copy_weights: missing mandatory projections "
                f"{missing_after} from {src.__class__.__name__}."
            )

        target_map = {
            "q": self.q_proj,
            "k": self.k_proj,
            "v": self.v_proj,
            "o": self.out_proj,
        }

        with torch.no_grad():
            for proj_key, target_mod in target_map.items():
                w, b = extracted[proj_key]
                if w is None:
                    if proj_key == "o" and self.is_nested_encoder:
                        nn.init.eye_(target_mod.weight)
                        if target_mod.bias is not None:
                            nn.init.zeros_(target_mod.bias)
                        continue
                    else:
                        raise RuntimeError(f"QCQAAttention: missing weight for {proj_key}.")

                if w.shape == target_mod.weight.shape:
                    target_mod.weight.copy_(w)
                elif w.t().contiguous().shape == target_mod.weight.shape:
                    target_mod.weight.copy_(w.t().contiguous())
                elif (
                    w.shape[0] < target_mod.weight.shape[0]
                    and target_mod.weight.shape[0] % w.shape[0] == 0
                    and w.shape[1] == target_mod.weight.shape[1]
                ):
                    repeats = target_mod.weight.shape[0] // w.shape[0]
                    target_mod.weight.copy_(w.repeat(repeats, 1))
                else:
                    min_0 = min(target_mod.weight.shape[0], w.shape[0])
                    min_1 = min(target_mod.weight.shape[1], w.shape[1])
                    target_mod.weight.zero_()
                    target_mod.weight[:min_0, :min_1].copy_(w[:min_0, :min_1])

                if b is not None and target_mod.bias is not None:
                    if b.shape == target_mod.bias.shape:
                        target_mod.bias.copy_(b)
                    elif (
                        b.shape[0] < target_mod.bias.shape[0]
                        and target_mod.bias.shape[0] % b.shape[0] == 0
                    ):
                        repeats = target_mod.bias.shape[0] // b.shape[0]
                        target_mod.bias.copy_(b.repeat(repeats))
                    else:
                        min_b = min(target_mod.bias.shape[0], b.shape[0])
                        target_mod.bias.zero_()
                        target_mod.bias[:min_b].copy_(b[:min_b])
                elif target_mod.bias is not None:
                    nn.init.zeros_(target_mod.bias)

                norm = float(torch.linalg.norm(target_mod.weight.float()).item())
                if norm < 1e-4:
                    logger.warning(
                        "QCQAAttention: weight for '%s' has near-zero Frobenius norm (%.2e).",
                        proj_key,
                        norm,
                    )

        if self.freeze_base:
            for mod in [self.q_proj, self.k_proj, self.v_proj, self.out_proj]:
                mod.freeze_base_weights()

    # ------------------------------------------------------------------
    # QC-FIX-16: robust valid-mask helper (2D / 3D / 4D)
    # ------------------------------------------------------------------
    @staticmethod
    def _prepare_valid_mask(
        attention_mask: torch.Tensor | None,
        B: int,
        N_kv: int,
        device: torch.device,
    ) -> torch.Tensor | None:
        if attention_mask is None:
            return None
        if attention_mask.dim() == 2:
            if attention_mask.dtype == torch.bool:
                return attention_mask
            if attention_mask.dtype.is_floating_point:
                return attention_mask > -1e4
            return attention_mask > 0
        if attention_mask.dim() == 3:
            # (B, N_q, N_kv) or (B, 1, N_kv)
            if attention_mask.dtype == torch.bool:
                v = attention_mask
            elif attention_mask.dtype.is_floating_point:
                v = attention_mask > -1e4
            else:
                v = attention_mask > 0
            # If query axis has size > 1, aggregate (any valid).
            if v.shape[1] > 1:
                v = v.any(dim=1)
            else:
                v = v.squeeze(1)
            return v  # (B, N_kv)
        if attention_mask.dim() == 4:
            if attention_mask.dtype == torch.bool:
                v = attention_mask
            elif attention_mask.dtype.is_floating_point:
                v = attention_mask > -1e4
            else:
                v = attention_mask > 0
            return v.any(dim=-2).squeeze(1)  # (B, N_kv)
        raise ValueError(f"Unsupported attention_mask dim: {attention_mask.dim()}")

    # ------------------------------------------------------------------
    # Forward
    # ------------------------------------------------------------------
    def forward(
        self,
        hidden_states: torch.Tensor,
        attention_mask: torch.Tensor | None = None,
        head_mask: torch.Tensor | None = None,
        encoder_hidden_states: torch.Tensor | None = None,
        encoder_attention_mask: torch.Tensor | None = None,
        past_key_value: Any | None = None,
        output_attentions: bool | None = False,
        output_hidden_states: bool | None = False,
        return_dict: bool | None = True,
        position_embeddings: tuple[torch.Tensor, torch.Tensor] | None = None,
        layer_idx: int = 0,
        *args: Any,
        **kwargs: Any,
    ) -> tuple[torch.Tensor, torch.Tensor | None]:
        B, L, _ = hidden_states.shape
        device = hidden_states.device

        is_cross = encoder_hidden_states is not None
        kv_input = encoder_hidden_states if is_cross else hidden_states
        N_kv_new = kv_input.shape[1]

        # --- Projections ---
        q = self.q_proj(hidden_states).view(B, L, self.num_heads, self.head_dim)
        k_new = self.k_proj(kv_input).view(B, N_kv_new, self.num_kv_heads, self.head_dim)
        v_new = self.v_proj(kv_input).view(B, N_kv_new, self.num_kv_heads, self.head_dim)

        # --- RoPE (self-attention only) ---
        if position_embeddings is None:
            position_embeddings = kwargs.get("position_embeddings")
        if position_embeddings is not None and not is_cross:
            cos, sin = position_embeddings
            past_len_rope = 0
            if past_key_value is not None:
                if isinstance(past_key_value, (tuple, list)) and len(past_key_value) >= 1:
                    past_len_rope = past_key_value[0].shape[-2]
                elif hasattr(past_key_value, "key_cache") and past_key_value.key_cache:
                    idx = min(layer_idx, len(past_key_value.key_cache) - 1)
                    past_len_rope = past_key_value.key_cache[idx].shape[-2]
            # QC-FIX-19: cos/sin must cover both q and k new tokens.
            cos_slice = cos[..., past_len_rope : past_len_rope + N_kv_new, :]
            sin_slice = sin[..., past_len_rope : past_len_rope + N_kv_new, :]

            # q uses the first L of these positions; k uses the last N_kv_new (== same if no cross)
            q_t = q.permute(0, 2, 1, 3).contiguous()  # (B, H_q, L, d)
            k_t = k_new.permute(0, 2, 1, 3).contiguous()  # (B, H_kv, N_kv_new, d)

            # Use slices matching L for q and N_kv_new for k.
            cos_q = cos_slice[..., :L, :]
            sin_q = sin_slice[..., :L, :]
            cos_k = cos_slice[..., :N_kv_new, :]
            sin_k = sin_slice[..., :N_kv_new, :]
            q_rot, _ = apply_rotary_pos_emb(q_t, q_t, cos_q, sin_q)
            _, k_rot = apply_rotary_pos_emb(k_t, k_t, cos_k, sin_k)
            q = q_rot.permute(0, 2, 1, 3).contiguous()
            k_new = k_rot.permute(0, 2, 1, 3).contiguous()

        # --- KV cache ---
        past_k = past_v = None
        if past_key_value is not None and not is_cross:
            if isinstance(past_key_value, (tuple, list)) and len(past_key_value) >= 2:
                past_k, past_v = past_key_value[0], past_key_value[1]
            elif hasattr(past_key_value, "key_cache") and past_key_value.key_cache:
                idx = min(layer_idx, len(past_key_value.key_cache) - 1)
                past_k = past_key_value.key_cache[idx]
                past_v = past_key_value.value_cache[idx]

        if past_k is not None and not is_cross:
            K_cat = torch.cat([past_k, k_new], dim=1)  # (B, N_kv, H_kv, d)
            V_cat = torch.cat([past_v, v_new], dim=1)
        else:
            K_cat = k_new
            V_cat = v_new

        if past_key_value is not None and hasattr(past_key_value, "update") and not is_cross:
            past_key_value.update(k_new, v_new, layer_idx)

        N_kv = K_cat.shape[1]
        past_len = N_kv - N_kv_new if (self.is_decoder and not is_cross) else 0

        # ============================================================
        # QC-FIX-13: Dynamic routing → head-level KV synthesis → MHA
        # ============================================================
        # Router: per-token distribution over KV heads
        # q: (B, L, H_q, d) → router → (B, L, H_q, H_kv)
        route_logits = self.router(q) / max(self.router_temp, 1e-4)
        route_weights = F.softmax(route_logits.float(), dim=-1).to(q.dtype)  # (B, L, H_q, H_kv)

        # Aggregate over query positions to get head-level routing.
        # This keeps the routing input-dependent (from q) while remaining
        # computationally tractable and semantically meaningful.
        w_head = route_weights.mean(dim=1)  # (B, H_q, H_kv)
        w_head = w_head / w_head.sum(dim=-1, keepdim=True).clamp(min=1e-9)

        # Mix KV heads: k_cat[b, h_q, j, d] = Σ_{h_kv} w_head[b, h_q, h_kv] · k[b, j, h_kv, d]
        K_perm = K_cat.permute(0, 2, 1, 3)  # (B, H_kv, N_kv, d)
        V_perm = V_cat.permute(0, 2, 1, 3)
        # einsum: w_head[b,h_q,h_kv] · K_perm[b,h_kv,j,d] → (B, H_q, N_kv, d)
        K_mixed = torch.einsum("bqk,bkjd->bqjd", w_head, K_perm)  # (B, H_q, N_kv, d)
        V_mixed = torch.einsum("bqk,bkjd->bqjd", w_head, V_perm)

        # Prepare q for attention
        q_heads = q.permute(0, 2, 1, 3).contiguous()  # (B, H_q, L, d)

        scale = 1.0 / math.sqrt(self.head_dim)

        # Causal mask (decoder only)
        causal_mask = None
        if self.is_decoder and not is_cross:
            if past_len > 0:
                abs_q = (past_len + torch.arange(L, device=device)).unsqueeze(1)
                abs_k = torch.arange(N_kv, device=device).unsqueeze(0)
                causal = (abs_k <= abs_q).unsqueeze(0).unsqueeze(0)  # (1, 1, L, N_kv)
            else:
                causal = (
                    torch.tril(torch.ones(L, N_kv, device=device, dtype=torch.bool))
                    .unsqueeze(0)
                    .unsqueeze(0)
                )
            causal_mask = causal

        # Padding mask
        eff_mask = encoder_attention_mask if is_cross else attention_mask
        token_valid = self._prepare_valid_mask(eff_mask, B, N_kv, device)

        # --- Fast SDPA path (QC-FIX-18) ---
        # Build additive bias for SDPA
        attn_bias_sdpa = None
        if not output_attentions and head_mask is None:
            bias_parts = []
            if causal_mask is not None:
                causal_bias = torch.zeros(1, 1, L, N_kv, device=device, dtype=torch.float32)
                causal_bias.masked_fill_(~causal_mask, -1e4)
                bias_parts.append(causal_bias)
            if token_valid is not None:
                pad_bias = torch.zeros(1, 1, 1, N_kv, device=device, dtype=torch.float32)
                pad_bias.masked_fill_(~token_valid[:, None, None, :].bool(), -1e4)
                bias_parts.append(pad_bias)
            if bias_parts:
                combined = sum(bias_parts)
                attn_bias_sdpa = combined.to(K_mixed.dtype)

        if attn_bias_sdpa is not None or (causal_mask is None and token_valid is None):
            try:
                q_sdp = q_heads.to(torch.float16) if q_heads.dtype == torch.float32 else q_heads
                k_sdp = K_mixed.to(torch.float16) if K_mixed.dtype == torch.float32 else K_mixed
                v_sdp = V_mixed.to(torch.float16) if V_mixed.dtype == torch.float32 else V_mixed

                out_sdp = F.scaled_dot_product_attention(
                    q_sdp,
                    k_sdp,
                    v_sdp,
                    attn_mask=attn_bias_sdpa,
                    is_causal=False,
                    dropout_p=self.dropout.p if self.training else 0.0,
                )
                context = (
                    out_sdp.to(q.dtype)
                    .permute(0, 2, 1, 3)
                    .contiguous()
                    .view(B, L, self.all_head_size)
                )
                context = torch.nan_to_num(context, nan=0.0, posinf=1e4, neginf=-1e4)

                if self.is_nested_encoder:
                    return context, None
                out = self.out_proj(context)
                out = torch.nan_to_num(out, nan=0.0, posinf=1e4, neginf=-1e4)
                return out, None
            except Exception as e:
                logger.debug("QCQA SDPA path failed: %s; falling back to manual.", e)

        # --- Manual path (needed when output_attentions or head_mask) ---
        scores = (
            torch.matmul(
                q_heads.float(),
                K_mixed.float().transpose(-2, -1).contiguous(),
            )
            * scale
        )  # (B, H_q, L, N_kv)

        if causal_mask is not None:
            scores = scores.masked_fill(~causal_mask, -1e4)

        if token_valid is not None:
            scores = scores.masked_fill(~token_valid[:, None, None, :].bool(), -1e4)

        scores = torch.nan_to_num(scores, nan=-1e4, posinf=1e4, neginf=-1e4)
        attn_probs = F.softmax(scores, dim=-1).to(q.dtype)
        attn_probs = torch.nan_to_num(attn_probs, nan=0.0)
        attn_probs = self.dropout(attn_probs)

        if head_mask is not None:
            if head_mask.dim() == 1:
                head_mask = head_mask.view(1, -1, 1, 1)
            elif head_mask.dim() == 2:
                head_mask = head_mask.unsqueeze(-1).unsqueeze(-1)
            elif head_mask.dim() == 3:
                head_mask = head_mask[:, :, :1].unsqueeze(-1)
            attn_probs = attn_probs * head_mask.to(attn_probs.dtype)

        # Context: (B, H_q, L, N_kv) @ (B, H_q, N_kv, d) → (B, H_q, L, d)
        context = torch.matmul(attn_probs, V_mixed)
        context = context.permute(0, 2, 1, 3).contiguous().view(B, L, self.all_head_size)
        context = torch.nan_to_num(context, nan=0.0, posinf=1e4, neginf=-1e4)

        if self.is_nested_encoder:
            return context, (attn_probs if output_attentions else None)

        out = self.out_proj(context)
        out = torch.nan_to_num(out, nan=0.0, posinf=1e4, neginf=-1e4)
        return out, (attn_probs if output_attentions else None)

Every custom attention module must inherit from this.

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Ancestors

• BaseAttention
• torch.nn.modules.module.Module

Class variables

var is_custom_attention : bool

The type of the None singleton.

Inherited members

• BaseAttention:
  • copy_weights
  • extra_repr
  • forward