Files
hao-ai-lab-FastVideo/v2/runtime/__init__.py
T
SolitaryThinker 32a7a6b87b [feat] Three stress tests: interactive sessions, workflow RL, heterogeneous co-scheduling
Targets the three design_v3 claims that were most load-bearing AND least
exercised (sessions/realtime, training-plane boundary, the WorkUnit-generality
falsifier). All fit with no new runtime primitive (127 tests pass).

1. Interactive world-model session (runtime/session.py, §9.8) — the Session
   plane had ZERO coverage. WorldModelSession drives the causal chunk_rollout
   loop as a long-lived session: persistent cross-request world state on the
   Session.kv_handle, frame streaming, transactional step-boundary cancellation
   (a cancelled act leaves the world resumable), no cross-session smearing.
   Added only a continuation seam to the chunk loop (init seeds context from a
   world_context slot; default empty = unchanged one-shot path). 5 tests.

2. End-to-end RL over a cross-model workflow (training/methods/workflow_rl.py,
   §9.9) — trains BOTH flux-t2i and wan-i2v from ONE final-video reward. Rolls
   out the whole workflow with SDE capture in both instances; the same final
   advantage drives FlowGRPO PPO on each stage's transformer; two WeightSyncPlans
   on two instances. The earlier model (T2I) is trained by a reward on the final
   video — end-to-end credit across a model boundary — proven causal by a control
   (constant reward => zero advantage => nothing moves). 4 tests.

3. Heterogeneous WorkUnit co-scheduling (models/tiled/, §9.10) — the §17
   falsifier. VAETileLoop makes VAE decode a loop of VAE_TILE units; tiling is
   exact (== one-shot, C0), and VAE_TILE + DIFFUSION_STEP pipelines interleave
   bit-identically and co-run in one batch. Validates the mechanism; the
   economic half (does it pay) stays a port-time measurement. 4 tests.

designv4 §9.8–§9.10 + falsifier/layout/closing updates (127 tests, 20 files).
2026-07-04 17:15:34 +00:00

23 lines
914 B
Python

"""Execution plane — engine + scheduler (design_v3 §6)."""
from __future__ import annotations
from .async_engine import AsyncEngine, RequestState
from .context import RuntimeLoopContext
from .disaggregated import DisaggregatedRunner
from .engine import Engine, ProgramRunner
from .pools import DeployConfig, PoolSet, RolePool, RolePoolSpec, wan_t2v_disaggregated
from .session import WorldModelSession
from .scheduler import (
AdmissionController,
AdmissionInfeasible,
BatchScheduler,
SchedulerMetrics,
StepTicket,
WorkUnit,
)
__all__ = ["Engine", "ProgramRunner", "RuntimeLoopContext", "AdmissionController",
"AdmissionInfeasible", "BatchScheduler", "SchedulerMetrics", "StepTicket", "WorkUnit",
"AsyncEngine", "RequestState", "DisaggregatedRunner", "WorldModelSession",
"DeployConfig", "PoolSet", "RolePool", "RolePoolSpec", "wan_t2v_disaggregated"]