# KDA spec verify from one checkpoint state per request, ported from Kimi-K3's
# RecoverSSM (fixes/recoverssm.py). On with this file;
# VLLM_GLM5NEXT_RECOVERSSM=0 turns it off. The stock spec path keeps 1 + k recurrent states
# per request and writes one per verified token. This verifies from the
# checkpoint, records each token's inputs, and after sampling replays only
# the accepted tokens into it. Each request then holds one KDA block per
# group, where the stock path holds 1 + k (8 at k=7). The records cost
# ~3.2 MiB per max_num_seqs row per rank, outside the pinned pool.
# Stack after fixes.yaml (kda.py, causal_conv1d.py). model.py is sp.yaml's
# file: it installs the runner's commit hook, and SP stays off without sp.yaml.
services:
  glm53:
    volumes:
      - ../experimental/fixes/recoverssm.py:/usr/local/lib/python3.12/dist-packages/vllm/models/glm5next/common/recoverssm.py:ro
      - ../experimental/fixes/model.py:/usr/local/lib/python3.12/dist-packages/vllm/models/glm5next/common/model.py:ro
    environment:
      - VLLM_GLM5NEXT_RECOVERSSM=${VLLM_GLM5NEXT_RECOVERSSM:-1}