feat: implement DGR-006 tensor bundle boundary
This commit is contained in:
@@ -328,6 +328,8 @@ def decode_tensor(
|
||||
def encode_bundle(
|
||||
tensors: Iterable[pb.NamedTensor],
|
||||
*,
|
||||
architecture: int = pb.ARCHITECTURE_TYPE_UNSPECIFIED,
|
||||
boundary_point: str = "",
|
||||
max_chunk_bytes: int = DEFAULT_MAX_CHUNK_BYTES,
|
||||
max_tensors: int = DEFAULT_MAX_TENSORS_PER_BUNDLE,
|
||||
) -> pb.TensorBundle:
|
||||
@@ -338,7 +340,12 @@ def encode_bundle(
|
||||
raise ProtocolError(
|
||||
f"bundle carries {len(tensor_list)} tensors, exceeding limit {max_tensors}"
|
||||
)
|
||||
bundle = pb.TensorBundle(bundle_version=BUNDLE_VERSION, tensors=tensor_list)
|
||||
bundle = pb.TensorBundle(
|
||||
bundle_version=BUNDLE_VERSION,
|
||||
tensors=tensor_list,
|
||||
architecture=architecture,
|
||||
boundary_point=boundary_point,
|
||||
)
|
||||
if bundle.ByteSize() > max_chunk_bytes:
|
||||
raise ProtocolError(
|
||||
f"serialized tensor bundle exceeds the {max_chunk_bytes}-byte "
|
||||
@@ -392,6 +399,80 @@ def decode_bundle(
|
||||
return payloads
|
||||
|
||||
|
||||
def encode_decode_step(
|
||||
bundle: pb.TensorBundle,
|
||||
*,
|
||||
idempotency_step: int,
|
||||
position: int,
|
||||
expected_past_len: int,
|
||||
work_id: str,
|
||||
deadline_unix_nanos: int = 0,
|
||||
prefer_compact_one_tensor: bool = True,
|
||||
) -> pb.DecodeStep:
|
||||
"""Encode a decode boundary, retaining the deliberate compact fallback."""
|
||||
step = pb.DecodeStep(
|
||||
idempotency_step=idempotency_step,
|
||||
position=position,
|
||||
expected_past_len=expected_past_len,
|
||||
work_id=work_id,
|
||||
deadline_unix_nanos=deadline_unix_nanos,
|
||||
)
|
||||
if prefer_compact_one_tensor and len(bundle.tensors) == 1:
|
||||
step.tensor.CopyFrom(bundle.tensors[0])
|
||||
else:
|
||||
step.bundle.CopyFrom(bundle)
|
||||
return step
|
||||
|
||||
|
||||
def validate_tail_result(result: pb.TailResult) -> None:
|
||||
"""Fail closed unless a tail completion is bound to its exact recipe."""
|
||||
identity = result.identity
|
||||
required = (
|
||||
identity.request_id,
|
||||
identity.runtime_recipe_digest,
|
||||
identity.chat_template_id,
|
||||
identity.chat_template_version,
|
||||
identity.reasoning_mode,
|
||||
)
|
||||
if not all(required) or identity.architecture == pb.ARCHITECTURE_TYPE_UNSPECIFIED:
|
||||
raise ProtocolError("tail result lacks exact request/recipe/template identity")
|
||||
if result.WhichOneof("output") not in {"logits", "sampled_token_id"}:
|
||||
raise ProtocolError("tail result lacks logits or sampled token output")
|
||||
|
||||
|
||||
def decode_step_bundle(
|
||||
step: pb.DecodeStep,
|
||||
*,
|
||||
max_chunk_bytes: int = DEFAULT_MAX_CHUNK_BYTES,
|
||||
max_fragment_bytes: int = DEFAULT_MAX_FRAGMENT_BYTES,
|
||||
max_fragments: int = DEFAULT_MAX_FRAGMENTS_PER_TENSOR,
|
||||
max_tensors: int = DEFAULT_MAX_TENSORS_PER_BUNDLE,
|
||||
) -> dict[str, bytes]:
|
||||
"""Decode a fast-path boundary with the DGR-006 compatibility rule.
|
||||
|
||||
`bundle` is authoritative because it can carry architecture sidebands. The
|
||||
old `tensor` field remains the compact representation for a certified
|
||||
one-tensor boundary and is accepted by new readers during rollout.
|
||||
"""
|
||||
if step.HasField("bundle"):
|
||||
return decode_bundle(
|
||||
step.bundle,
|
||||
max_chunk_bytes=max_chunk_bytes,
|
||||
max_fragment_bytes=max_fragment_bytes,
|
||||
max_fragments=max_fragments,
|
||||
max_tensors=max_tensors,
|
||||
)
|
||||
if step.HasField("tensor"):
|
||||
return decode_bundle(
|
||||
encode_bundle([step.tensor], max_chunk_bytes=max_chunk_bytes),
|
||||
max_chunk_bytes=max_chunk_bytes,
|
||||
max_fragment_bytes=max_fragment_bytes,
|
||||
max_fragments=max_fragments,
|
||||
max_tensors=max_tensors,
|
||||
)
|
||||
raise ProtocolError("decode step carries neither TensorBundle nor legacy tensor")
|
||||
|
||||
|
||||
def validate_session_message_size(
|
||||
message: pb.SessionRequest | pb.SessionResponse,
|
||||
*,
|
||||
|
||||
Reference in New Issue
Block a user