# MTP draft-model quant workaround for vLLM 0.24.0 — MUST be named sitecustomize.py and be on
# PYTHONPATH so it loads in the vLLM engine-core subprocess. Mount its directory into the serve
# container and set -e PYTHONPATH=<mount>.
#
# THE BUG: vLLM 0.24.0 does not propagate the main model's modelopt `exclude_modules` to the
# spec-decode DRAFT model (Qwen3_5MTP). So the drafter builds its own qkv_proj/gate_up_proj as
# NVFP4-quantized while the grafted MTP head is BF16 → `AssertionError: param_data.shape ==
# loaded_weight.shape` in qwen3_5_mtp.py:256, engine-core dies during weight load. Instrumenting
# is_layer_skipped proved the drafter's exclude list only ever contains the *main* model's
# entries, never the mtp ones — so no checkpoint config can fix it. (Also: is_layer_skipped does
# exact string membership, not glob — wildcards like `mtp.layers.0.*` match nothing.)
#
# THE FIX: force is_layer_skipped to return True (skip = keep BF16) for any `mtp.*` layer, so the
# draft head stays unquantized and its BF16 weights load. Report upstream: draft-model quant
# config should inherit the target model's exclude_modules.
import importlib.abc
import importlib.util
import sys

TARGET = "vllm.model_executor.layers.quantization.utils.quant_utils"


class _Finder(importlib.abc.MetaPathFinder):
    def find_spec(self, name, path, target=None):
        if name != TARGET:
            return None
        sys.meta_path.remove(self)
        try:
            spec = importlib.util.find_spec(name)
        finally:
            sys.meta_path.insert(0, self)
        if not spec or not spec.loader:
            return None
        _orig_exec = spec.loader.exec_module

        def exec_module(module):
            _orig_exec(module)
            _orig_isls = module.is_layer_skipped

            def is_layer_skipped(prefix, ignored_layers, *args, **kwargs):
                pl = str(prefix)
                if pl.startswith("mtp.") or ".mtp." in pl:
                    return True  # keep the mtp draft head BF16
                return _orig_isls(prefix, ignored_layers, *args, **kwargs)

            module.is_layer_skipped = is_layer_skipped
            print("[mtp-workaround] is_layer_skipped force-skip for mtp.* installed", flush=True)

        spec.loader.exec_module = exec_module
        return spec


sys.meta_path.insert(0, _Finder())