# Composable-parallel strategy for Qwen2.5-Omni: tensor-parallel the thinker.
#
# Shard the thinker stage across 2 GPUs with tensor parallelism (TP=2). TP routing
# is fixed (broadcast), so no `routing` / load-balancer policy is involved -- this
# is the simplest axis and a good starting point for the mental model.
#
# The strategy sets tensor_parallel_size=2 on the thinker. Rather than hand-write a
# bespoke deploy YAML, run on the bundled default deploy config and pass a matching
# 2-GPU device layout via --stage-overrides (explicit kwargs), so the thinker gets a
# two-GPU pool while talker + code2wav share a third card. Requires >= 3 GPUs.
#
# Usage:
#   python3 end2end.py --query-type text --num-prompts 6 \
#       --strategy-config strategy_tp2.yaml \
#       --stage-overrides '{"0": {"devices": "0,1"}, "1": {"devices": "2"}, "2": {"devices": "2"}}'
strategies:
  thinker:
    - axis: tp
      size: 2