"""vLLM general plugin: install the cheap Qwen3.8-Flash-Next MTP drafter (q38_draft.py) in every vLLM process.
Inactive unless Q38_DRAFT_VOCAB is set, so the same environment still runs unpatched servers.
  Q38_DRAFT_HOME    directory holding q38_draft.py / nvfp4_ops.py (this repo's mtp_draft/)
  Q38_DRAFT_VOCAB   draft vocabulary mask (.pt bool[248320]); empty -> plugin inactive
  Q38_DRAFT_HEAD_Q  marlin (default) | cutlass | bf16      draft lm_head
  Q38_DRAFT_MTP_Q   marlin (default) | cutlass | bf16      MTP block BF16 linears
"""
import os
import sys


def main():
    if not os.environ.get("Q38_DRAFT_VOCAB"):
        return
    home = os.environ.get("Q38_DRAFT_HOME")
    if home and home not in sys.path:
        sys.path.insert(0, home)
    import q38_draft
    q38_draft.install_from_env()