SolitaryThinker
4e331eb7ff
Mechanical conversion of every relative import under v2/ to an absolute v2.* path (from .x / ..x / ...x -> from v2.<pkg>.x) so imports are unambiguous, grep-able, and stable when code is copied/moved between entrypoints (VideoGenerator, CLI, server). Surgical prefix-only rewrite: only the 'from <dots><module>' prefix changed — import names, parentheses, multi-line formatting, comments, and ordering are byte-for-byte preserved (no collapsing, no reorder, no unrelated reformatting). - 471 imports across 125 files; v2/tests/ was already absolute (untouched). - Validated: all 125 files compile, every 'from v2.* import' target resolves to a real module/package, zero relative imports remain (full sweep), CPU mini suite green (202 passed, 2 skipped).
59 lines
2.1 KiB
Python
59 lines
2.1 KiB
Python
"""FakeDeviceMesh — a ParallelDims-style builder, CPU-testable (design_v3 §8; torchtitan).
|
|
|
|
> Declarative, validated, compiled to a PyTorch ``DeviceMesh`` via a ``ParallelDims``-
|
|
> style builder (product-of-degrees validation, cached submeshes).
|
|
|
|
On a GPU box this compiles to ``torch.distributed.device_mesh.DeviceMesh``. Here it is a
|
|
pure-Python mesh of rank tuples so topology logic is unit-tested without GPUs.
|
|
Degree-one axes exist as trivial groups so component code needs no special cases.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from itertools import product
|
|
|
|
from v2.parallel.plan import ParallelPlan
|
|
from v2.parallel.validation import validate_plan
|
|
|
|
|
|
class FakeDeviceMesh:
|
|
def __init__(self, plan: ParallelPlan):
|
|
self.plan = plan
|
|
self.order = plan.mesh_order or list(plan.axes.keys())
|
|
self.shape = tuple(plan.degree(a) for a in self.order)
|
|
self.world_size = plan.world_size()
|
|
|
|
def group_ranks(self, axis: str) -> list[list[int]]:
|
|
"""All collective groups along one axis (each is a list of global ranks)."""
|
|
if axis not in self.order:
|
|
return [[0]] # degree-one trivial group
|
|
axis_idx = self.order.index(axis)
|
|
groups: list[list[int]] = []
|
|
ranges = [range(d) for d in self.shape]
|
|
seen: set[tuple] = set()
|
|
for coord in product(*ranges):
|
|
key = coord[:axis_idx] + coord[axis_idx + 1:]
|
|
if key in seen:
|
|
continue
|
|
seen.add(key)
|
|
group = []
|
|
for i in range(self.shape[axis_idx]):
|
|
c = list(coord)
|
|
c[axis_idx] = i
|
|
group.append(self._coord_to_rank(tuple(c)))
|
|
groups.append(group)
|
|
return groups
|
|
|
|
def _coord_to_rank(self, coord: tuple[int, ...]) -> int:
|
|
rank = 0
|
|
for c, d in zip(coord, self.shape):
|
|
rank = rank * d + c
|
|
return rank
|
|
|
|
def __repr__(self) -> str:
|
|
return f"FakeDeviceMesh(order={self.order}, shape={self.shape}, world={self.world_size})"
|
|
|
|
|
|
def build_mesh(plan: ParallelPlan, card=None, **kw) -> FakeDeviceMesh:
|
|
validate_plan(plan, card=card, **kw)
|
|
return FakeDeviceMesh(plan)
|