[AutoDeploy]: Investigate SuperV3 with MTP not scaling well

[galagam]

🚀 The feature, motivation and pitch

AD surpasses PT at WS=1 across all concurrencies — 18% faster at c=1, near-parity (1%) at c=64.
AD fails to scale at WS=4: PT leads by 20–35%. The gap is driven by poor WS=1→4 scaling on the AD side: PT scales 1.52× from WS=1 to WS=4 at c=1 (4.67ms→3.07ms), while AD only gains 1.04× (3.82ms→3.67ms).

Investigate and resolve the poor scaling on AutoDeploy side.
Baseline branch: nv-auto-deploy:gagam/super-mtp-perf-2-replay (see #13725)

Alternatives

No response

Additional context

See SuperV3 MTP ticket #12359
Scripts, configs and experiment data:
https://gitlab-master.nvidia.com/ghubaraagam/agent-reports/-/tree/main/260428_superv3_mtp?ref_type=heads

Before submitting a new issue...

• Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

[galagam]

@MrGeva Pushing anything to main seems hopeless at this point. I cleaned up and rebased, hopefully you can take it from here while I keep battling CI issues.

[MrGeva]

@galagam ack

[MrGeva]