modeling_mlx_qwen36_modelopt_hybrid.py

"""MLX runtime for Qwen3.6 ModelOpt hybrid FP8/NVFP4 checkpoints.

The converter stores ModelOpt FP8 weights losslessly in MLX's packed MXFP8
carrier with unit E8M0 block scales, then applies the original per-tensor
ModelOpt scale to the output.  ModelOpt NVFP4 weights and E4M3 block scales
are likewise retained bit-for-bit; their FP32 tensor scale is applied after
the matrix multiplication.

Activations remain in the model dtype.  This avoids adding a second lossy
activation requantization scheme while still using MLX's native quantized
weight kernels.
"""

from dataclasses import dataclass, field
from typing import Dict

import mlx.core as mx
import mlx.nn as nn
from mlx.utils import tree_flatten, tree_unflatten

from mlx_lm.models.base import BaseModelArgs
from mlx_lm.models.qwen3_5_moe import Model as BaseModel
from mlx_lm.models.switch_layers import SwitchLinear


@dataclass
class ModelArgs(BaseModelArgs):
    model_type: str
    text_config: dict
    mlx_modelopt_quantization: Dict[str, str] = field(default_factory=dict)


class ScaledQuantizedLinear(nn.Module):
    """Weight-quantized dense linear with an additional tensor scale."""

    def __init__(
        self,
        input_dims: int,
        output_dims: int,
        *,
        group_size: int,
        bits: int,
        mode: str,
        bias: bool = False,
    ):
        super().__init__()
        if input_dims % group_size:
            raise ValueError(
                f"input_dims={input_dims} is not divisible by group_size={group_size}"
            )
        if (input_dims * bits) % 32:
            raise ValueError(
                f"input_dims={input_dims}, bits={bits} cannot be packed into uint32"
            )

        self.group_size = group_size
        self.bits = bits
        self.mode = mode
        self.weight = mx.zeros(
            (output_dims, input_dims * bits // 32), dtype=mx.uint32
        )
        self.scales = mx.zeros(
            (output_dims, input_dims // group_size), dtype=mx.uint8
        )
        self.global_scale = mx.ones((), dtype=mx.float32)
        if bias:
            self.bias = mx.zeros((output_dims,))
        self.freeze()

    @classmethod
    def from_linear(cls, linear: nn.Module, kind: str):
        output_dims, input_dims = linear.weight.shape
        has_bias = linear.get("bias") is not None
        if kind == "scaled_mxfp8":
            params = dict(group_size=32, bits=8, mode="mxfp8")
        elif kind == "scaled_nvfp4":
            params = dict(group_size=16, bits=4, mode="nvfp4")
        else:
            raise ValueError(f"Unsupported dense quantization kind: {kind}")
        return cls(input_dims, output_dims, bias=has_bias, **params)

    def __call__(self, x):
        y = mx.quantized_matmul(
            x,
            self["weight"],
            self["scales"],
            transpose=True,
            group_size=self.group_size,
            bits=self.bits,
            mode=self.mode,
        )
        # Avoid promoting the residual stream to float32.
        y = y * self["global_scale"].astype(y.dtype)
        if "bias" in self:
            y = y + self["bias"]
        return y


class ScaledNVFP4SwitchLinear(nn.Module):
    """Expert linear using MLX gather_qmm and per-expert tensor scales."""

    group_size = 16
    bits = 4
    mode = "nvfp4"

    def __init__(
        self,
        input_dims: int,
        output_dims: int,
        num_experts: int,
        *,
        bias: bool = False,
    ):
        super().__init__()
        if input_dims % self.group_size:
            raise ValueError(
                f"input_dims={input_dims} is not divisible by {self.group_size}"
            )
        self.weight = mx.zeros(
            (num_experts, output_dims, input_dims * self.bits // 32),
            dtype=mx.uint32,
        )
        self.scales = mx.zeros(
            (num_experts, output_dims, input_dims // self.group_size),
            dtype=mx.uint8,
        )
        self.global_scales = mx.ones((num_experts,), dtype=mx.float32)
        if bias:
            self.bias = mx.zeros((num_experts, output_dims))
        self.freeze()

    @classmethod
    def from_switch_linear(cls, linear: SwitchLinear):
        num_experts, output_dims, input_dims = linear.weight.shape
        has_bias = linear.get("bias") is not None
        return cls(
            input_dims,
            output_dims,
            num_experts,
            bias=has_bias,
        )

    @property
    def input_dims(self):
        return self.scales.shape[2] * self.group_size

    @property
    def output_dims(self):
        return self.weight.shape[1]

    @property
    def num_experts(self):
        return self.weight.shape[0]

    def __call__(self, x, indices, sorted_indices=False):
        y = mx.gather_qmm(
            x,
            self["weight"],
            self["scales"],
            rhs_indices=indices,
            transpose=True,
            group_size=self.group_size,
            bits=self.bits,
            mode=self.mode,
            sorted_indices=sorted_indices,
        )
        scale = self["global_scales"][indices].astype(y.dtype)[..., None, None]
        y = y * scale
        if "bias" in self:
            y = y + mx.expand_dims(self["bias"][indices], -2)
        return y


def _replace_quantized_modules(model: nn.Module, quantization: Dict[str, str]):
    leaves = dict(
        tree_flatten(model.leaf_modules(), is_leaf=lambda m: isinstance(m, nn.Module))
    )
    missing = sorted(set(quantization) - set(leaves))
    if missing:
        preview = "\n  ".join(missing[:20])
        raise ValueError(f"Quantized module paths are absent from the model:\n  {preview}")

    for path, kind in quantization.items():
        module = leaves[path]
        if kind in ("scaled_mxfp8", "scaled_nvfp4"):
            if not isinstance(module, nn.Linear):
                raise TypeError(f"{path} is {type(module).__name__}, expected Linear")
            leaves[path] = ScaledQuantizedLinear.from_linear(module, kind)
        elif kind == "scaled_nvfp4_switch":
            if not isinstance(module, SwitchLinear):
                raise TypeError(
                    f"{path} is {type(module).__name__}, expected SwitchLinear"
                )
            leaves[path] = ScaledNVFP4SwitchLinear.from_switch_linear(module)
        else:
            raise ValueError(f"Unknown quantization kind {kind!r} for {path}")

    model.update_modules(tree_unflatten(list(leaves.items())))


class Model(BaseModel):
    def __init__(self, args: ModelArgs):
        super().__init__(args)
        _replace_quantized_modules(self, args.mlx_modelopt_quantization)