Will Lin
1fe50c0092
The v2 top level had grown to ~27 dirs + 13 loose files — half of them
single-concept abstraction shells (memory/ 86 LOC, transport/ 222, parity/ 178,
extend/ 226) and half vendored fastvideo code sitting as peers to the actual v2
design. Regroup to mirror README section 3 "Planes & dependency order":
core/ enums+types, card, loop, program, parity, request, parallel
(the model-native contracts; no kernels)
runtime/ + folded-in substrate: cache, memory, transport, extend
(the import graph shows only runtime consumes them; compile/cudagraph
already lived here)
serving/ + deploy/ (products / fleet)
_vendor/ all copied fastvideo: models, layers, attention, configs, distributed,
platforms, api, hooks, logging_utils, third_party + fastvideo_args/
utils/logger/envs/forward_context — internal layout unchanged, still
mirrors upstream for diffing
28 dirs + 13 root files -> 8 dirs + 6 root files. Pure mechanical move: 947
absolute-import paths rewritten (v2.X -> v2.{core,runtime,serving,_vendor}.X),
boundary-anchored so platform/ (native dispatch) and platforms/ (vendored CUDA
detect) no longer collide and neither does hooks/ vs extend/. Deleted the empty
v2/loader/. README section 3 + 16 updated; stale test count corrected
(34 files/216 tests -> 22 files/143 tests).
Validated: `import v2` stays torch-free; `v2/run_tests.py` and `pytest v2/tests/`
-> 143 passed, 2 skipped on the numpy toy backend. (On a GPU box force the toy
backend with CUDA_VISIBLE_DEVICES="" or detect() picks cuda.) No external importer
changed — examples use the re-exported `from v2 import VideoGenerator`.
69 lines
2.4 KiB
Python
69 lines
2.4 KiB
Python
"""LoopRunner — the only place iteration lives.
|
|
|
|
The runtime's driver, factored so the engine can either run it to completion
|
|
(``run``) or advance it one step at a time (``peek`` + ``step``) to **interleave** the steps
|
|
of concurrent requests. Per-request state is entirely in ``LoopState``; the runner holds no
|
|
hidden iteration state beyond a cached pending plan, so interleaving is safe by construction.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
from v2.core.loop.contracts import Done, LoopContext, LoopResult, LoopState, WorkPlan
|
|
|
|
|
|
class LoopRunner:
|
|
|
|
def __init__(self, loop: Any, ctx: LoopContext, request: Any, model: Any):
|
|
self.loop = loop
|
|
self.ctx = ctx
|
|
self.state: LoopState = loop.init(request, model, ctx)
|
|
self._done = False
|
|
self._result: LoopResult | None = None
|
|
self._pending: WorkPlan | None = None
|
|
|
|
@property
|
|
def done(self) -> bool:
|
|
return self._done
|
|
|
|
@property
|
|
def result(self) -> LoopResult | None:
|
|
return self._result
|
|
|
|
def peek(self) -> WorkPlan | None:
|
|
"""Compute (and cache) the next WorkPlan. ``next`` is kernel-free, so this is cheap.
|
|
Returns None when the loop is finished (and runs ``finalize`` exactly once)."""
|
|
if self._done:
|
|
return None
|
|
if self._pending is None:
|
|
self.ctx.check_cancel()
|
|
nxt = self.loop.next(self.state)
|
|
if isinstance(nxt, Done):
|
|
self._result = self.loop.finalize(self.state)
|
|
self._done = True
|
|
return None
|
|
self._pending = nxt
|
|
return self._pending
|
|
|
|
def step(self) -> bool:
|
|
"""Execute the pending plan (the inversion point) and fold the result in.
|
|
Returns True when the loop has just finished."""
|
|
plan = self.peek()
|
|
if self._done or plan is None:
|
|
return True
|
|
# the engine binds the current state onto ctx so interceptors see per-request state
|
|
if hasattr(self.ctx, "bind_state"):
|
|
self.ctx.bind_state(self.state)
|
|
result = self.ctx.execute(plan)
|
|
for chunk in plan.emits:
|
|
self.ctx.emit(chunk)
|
|
self.state = self.loop.advance(self.state, result)
|
|
self._pending = None
|
|
return self._done
|
|
|
|
def run(self) -> LoopResult:
|
|
while not self._done:
|
|
self.step()
|
|
assert self._result is not None
|
|
return self._result
|