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`.
61 lines
1.3 KiB
Python
61 lines
1.3 KiB
Python
"""Request plane — typed runtime objects crossing the product boundary."""
|
|
from __future__ import annotations
|
|
|
|
from v2.core.request.artifacts import (
|
|
Artifact,
|
|
AudioArtifact,
|
|
LatentArtifact,
|
|
Output,
|
|
TensorArtifact,
|
|
TextArtifact,
|
|
VideoArtifact,
|
|
)
|
|
from v2.core.request.cancel import CancelKind, Cancelled, CancelScope
|
|
from v2.core.request.modalpart import (
|
|
ActionPart,
|
|
AudioPart,
|
|
ImagePart,
|
|
LatentPart,
|
|
Modality,
|
|
ModalPart,
|
|
TextPart,
|
|
VideoPart,
|
|
)
|
|
from v2.core.request.params import CaptureMode, DiffusionParams, OutputSpec, SamplingParams
|
|
from v2.core.request.requests import Request, Session, make_request, new_request_id
|
|
from v2.core.request.streams import OmniEvent, Stream, StreamChunk
|
|
from v2.core.request.tasks import TaskType
|
|
|
|
__all__ = [
|
|
"TaskType",
|
|
"Modality",
|
|
"ModalPart",
|
|
"TextPart",
|
|
"ImagePart",
|
|
"VideoPart",
|
|
"AudioPart",
|
|
"ActionPart",
|
|
"LatentPart",
|
|
"SamplingParams",
|
|
"DiffusionParams",
|
|
"OutputSpec",
|
|
"CaptureMode",
|
|
"Request",
|
|
"Session",
|
|
"make_request",
|
|
"new_request_id",
|
|
"Artifact",
|
|
"VideoArtifact",
|
|
"AudioArtifact",
|
|
"TextArtifact",
|
|
"TensorArtifact",
|
|
"LatentArtifact",
|
|
"Output",
|
|
"Stream",
|
|
"OmniEvent",
|
|
"StreamChunk",
|
|
"CancelScope",
|
|
"CancelKind",
|
|
"Cancelled",
|
|
]
|