feat: implement DGR-006 tensor bundle boundary

This commit is contained in:
Dobromir Popov
2026-07-14 13:44:37 +03:00
parent 91c450840d
commit 7fb0050d22
16 changed files with 754 additions and 94 deletions

View File

@@ -27,6 +27,7 @@ TESTDATA_DIR = pathlib.Path(__file__).resolve().parents[2] / "native/testdata"
GOLDEN_SESSION_REQUEST = "session_request_golden.binpb"
GOLDEN_CAPABILITY_REPORT = "capability_report_golden.binpb"
GOLDEN_DECODE_STEP = "decode_step_golden.binpb"
# Written by the C++ conformance test into its build tree; the Python test picks
# it up when present to prove the two languages agree byte-for-byte.
@@ -136,6 +137,30 @@ def canonical_capability_report() -> pb.CapabilityReport:
)
def canonical_decode_step() -> pb.SessionRequest:
"""The DGR-006 multi-tensor decode boundary vector."""
hidden = codec.encode_tensor(
codec.HIDDEN_STATES, bytes(range(16)), [1, 1, 4], pb.DTYPE_FLOAT32
)
index_topk = codec.encode_tensor(
"index_topk", (3).to_bytes(4, "little"), [1], pb.DTYPE_INT32
)
return pb.SessionRequest(
decode=pb.DecodeStep(
idempotency_step=43,
position=384,
expected_past_len=384,
work_id="decode-7f3a",
deadline_unix_nanos=DEADLINE_UNIX_NANOS,
bundle=codec.encode_bundle(
[hidden, index_topk],
architecture=pb.ARCHITECTURE_TYPE_MLA,
boundary_point="pre_tail_residual",
),
)
)
def serialize(message) -> bytes:
"""Serialize deterministically, so committed golden bytes are stable."""
return message.SerializeToString(deterministic=True)