feat: DGR-002 - Adopt the versioned gRPC Shard protocol

This commit is contained in:
Dobromir Popov
2026-07-13 16:00:49 +03:00
parent efec84efef
commit 30dcf953fe
22 changed files with 3615 additions and 17 deletions

View File

@@ -0,0 +1,2 @@
# Generated by scripts/generate_native_protocol.py. Do not edit.
"""Generated protobuf/gRPC stubs for the native Shard protocol."""

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,525 @@
from google.protobuf.internal import containers as _containers
from google.protobuf.internal import enum_type_wrapper as _enum_type_wrapper
from google.protobuf import descriptor as _descriptor
from google.protobuf import message as _message
from collections.abc import Iterable as _Iterable, Mapping as _Mapping
from typing import ClassVar as _ClassVar, Optional as _Optional, Union as _Union
DESCRIPTOR: _descriptor.FileDescriptor
class SchemaVersion(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
__slots__ = ()
SCHEMA_VERSION_UNSPECIFIED: _ClassVar[SchemaVersion]
SCHEMA_VERSION_1: _ClassVar[SchemaVersion]
class DType(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
__slots__ = ()
DTYPE_UNSPECIFIED: _ClassVar[DType]
DTYPE_BFLOAT16: _ClassVar[DType]
DTYPE_FLOAT16: _ClassVar[DType]
DTYPE_FLOAT32: _ClassVar[DType]
DTYPE_INT32: _ClassVar[DType]
DTYPE_INT64: _ClassVar[DType]
DTYPE_UINT8: _ClassVar[DType]
DTYPE_INT8: _ClassVar[DType]
DTYPE_BOOL: _ClassVar[DType]
class ByteOrder(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
__slots__ = ()
BYTE_ORDER_UNSPECIFIED: _ClassVar[ByteOrder]
BYTE_ORDER_LITTLE_ENDIAN: _ClassVar[ByteOrder]
BYTE_ORDER_BIG_ENDIAN: _ClassVar[ByteOrder]
class Compression(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
__slots__ = ()
COMPRESSION_UNSPECIFIED: _ClassVar[Compression]
COMPRESSION_NONE: _ClassVar[Compression]
COMPRESSION_ZSTD: _ClassVar[Compression]
class ChecksumAlgorithm(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
__slots__ = ()
CHECKSUM_ALGORITHM_UNSPECIFIED: _ClassVar[ChecksumAlgorithm]
CHECKSUM_ALGORITHM_NONE: _ClassVar[ChecksumAlgorithm]
CHECKSUM_ALGORITHM_CRC32C: _ClassVar[ChecksumAlgorithm]
class Phase(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
__slots__ = ()
PHASE_UNSPECIFIED: _ClassVar[Phase]
PHASE_PREFILL: _ClassVar[Phase]
PHASE_DECODE: _ClassVar[Phase]
PHASE_RELEASE: _ClassVar[Phase]
PHASE_CANCEL: _ClassVar[Phase]
class CacheMode(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
__slots__ = ()
CACHE_MODE_UNSPECIFIED: _ClassVar[CacheMode]
CACHE_MODE_STATELESS: _ClassVar[CacheMode]
CACHE_MODE_PREFILL: _ClassVar[CacheMode]
CACHE_MODE_DECODE: _ClassVar[CacheMode]
class ErrorCode(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
__slots__ = ()
ERROR_CODE_UNSPECIFIED: _ClassVar[ErrorCode]
ERROR_CODE_SCHEMA_UNSUPPORTED: _ClassVar[ErrorCode]
ERROR_CODE_FINGERPRINT_MISMATCH: _ClassVar[ErrorCode]
ERROR_CODE_EPOCH_STALE: _ClassVar[ErrorCode]
ERROR_CODE_SHARD_RANGE_MISMATCH: _ClassVar[ErrorCode]
ERROR_CODE_CACHE_MISS: _ClassVar[ErrorCode]
ERROR_CODE_RESOURCE_EXHAUSTED: _ClassVar[ErrorCode]
ERROR_CODE_PAYLOAD_CORRUPT: _ClassVar[ErrorCode]
ERROR_CODE_CANCELLED: _ClassVar[ErrorCode]
ERROR_CODE_DEADLINE_EXCEEDED: _ClassVar[ErrorCode]
ERROR_CODE_FLOW_CONTROL_VIOLATION: _ClassVar[ErrorCode]
ERROR_CODE_INTERNAL: _ClassVar[ErrorCode]
class ServingState(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
__slots__ = ()
SERVING_STATE_UNSPECIFIED: _ClassVar[ServingState]
SERVING_STATE_SERVING: _ClassVar[ServingState]
SERVING_STATE_DRAINING: _ClassVar[ServingState]
SERVING_STATE_NOT_SERVING: _ClassVar[ServingState]
SCHEMA_VERSION_UNSPECIFIED: SchemaVersion
SCHEMA_VERSION_1: SchemaVersion
DTYPE_UNSPECIFIED: DType
DTYPE_BFLOAT16: DType
DTYPE_FLOAT16: DType
DTYPE_FLOAT32: DType
DTYPE_INT32: DType
DTYPE_INT64: DType
DTYPE_UINT8: DType
DTYPE_INT8: DType
DTYPE_BOOL: DType
BYTE_ORDER_UNSPECIFIED: ByteOrder
BYTE_ORDER_LITTLE_ENDIAN: ByteOrder
BYTE_ORDER_BIG_ENDIAN: ByteOrder
COMPRESSION_UNSPECIFIED: Compression
COMPRESSION_NONE: Compression
COMPRESSION_ZSTD: Compression
CHECKSUM_ALGORITHM_UNSPECIFIED: ChecksumAlgorithm
CHECKSUM_ALGORITHM_NONE: ChecksumAlgorithm
CHECKSUM_ALGORITHM_CRC32C: ChecksumAlgorithm
PHASE_UNSPECIFIED: Phase
PHASE_PREFILL: Phase
PHASE_DECODE: Phase
PHASE_RELEASE: Phase
PHASE_CANCEL: Phase
CACHE_MODE_UNSPECIFIED: CacheMode
CACHE_MODE_STATELESS: CacheMode
CACHE_MODE_PREFILL: CacheMode
CACHE_MODE_DECODE: CacheMode
ERROR_CODE_UNSPECIFIED: ErrorCode
ERROR_CODE_SCHEMA_UNSUPPORTED: ErrorCode
ERROR_CODE_FINGERPRINT_MISMATCH: ErrorCode
ERROR_CODE_EPOCH_STALE: ErrorCode
ERROR_CODE_SHARD_RANGE_MISMATCH: ErrorCode
ERROR_CODE_CACHE_MISS: ErrorCode
ERROR_CODE_RESOURCE_EXHAUSTED: ErrorCode
ERROR_CODE_PAYLOAD_CORRUPT: ErrorCode
ERROR_CODE_CANCELLED: ErrorCode
ERROR_CODE_DEADLINE_EXCEEDED: ErrorCode
ERROR_CODE_FLOW_CONTROL_VIOLATION: ErrorCode
ERROR_CODE_INTERNAL: ErrorCode
SERVING_STATE_UNSPECIFIED: ServingState
SERVING_STATE_SERVING: ServingState
SERVING_STATE_DRAINING: ServingState
SERVING_STATE_NOT_SERVING: ServingState
class Checksum(_message.Message):
__slots__ = ("algorithm", "value")
ALGORITHM_FIELD_NUMBER: _ClassVar[int]
VALUE_FIELD_NUMBER: _ClassVar[int]
algorithm: ChecksumAlgorithm
value: bytes
def __init__(self, algorithm: _Optional[_Union[ChecksumAlgorithm, str]] = ..., value: _Optional[bytes] = ...) -> None: ...
class TensorFragment(_message.Message):
__slots__ = ("fragment_index", "fragment_count", "byte_offset", "payload")
FRAGMENT_INDEX_FIELD_NUMBER: _ClassVar[int]
FRAGMENT_COUNT_FIELD_NUMBER: _ClassVar[int]
BYTE_OFFSET_FIELD_NUMBER: _ClassVar[int]
PAYLOAD_FIELD_NUMBER: _ClassVar[int]
fragment_index: int
fragment_count: int
byte_offset: int
payload: bytes
def __init__(self, fragment_index: _Optional[int] = ..., fragment_count: _Optional[int] = ..., byte_offset: _Optional[int] = ..., payload: _Optional[bytes] = ...) -> None: ...
class NamedTensor(_message.Message):
__slots__ = ("name", "shape", "dtype", "byte_order", "total_bytes", "compression", "checksum", "fragments")
NAME_FIELD_NUMBER: _ClassVar[int]
SHAPE_FIELD_NUMBER: _ClassVar[int]
DTYPE_FIELD_NUMBER: _ClassVar[int]
BYTE_ORDER_FIELD_NUMBER: _ClassVar[int]
TOTAL_BYTES_FIELD_NUMBER: _ClassVar[int]
COMPRESSION_FIELD_NUMBER: _ClassVar[int]
CHECKSUM_FIELD_NUMBER: _ClassVar[int]
FRAGMENTS_FIELD_NUMBER: _ClassVar[int]
name: str
shape: _containers.RepeatedScalarFieldContainer[int]
dtype: DType
byte_order: ByteOrder
total_bytes: int
compression: Compression
checksum: Checksum
fragments: _containers.RepeatedCompositeFieldContainer[TensorFragment]
def __init__(self, name: _Optional[str] = ..., shape: _Optional[_Iterable[int]] = ..., dtype: _Optional[_Union[DType, str]] = ..., byte_order: _Optional[_Union[ByteOrder, str]] = ..., total_bytes: _Optional[int] = ..., compression: _Optional[_Union[Compression, str]] = ..., checksum: _Optional[_Union[Checksum, _Mapping]] = ..., fragments: _Optional[_Iterable[_Union[TensorFragment, _Mapping]]] = ...) -> None: ...
class TensorBundle(_message.Message):
__slots__ = ("bundle_version", "tensors")
BUNDLE_VERSION_FIELD_NUMBER: _ClassVar[int]
TENSORS_FIELD_NUMBER: _ClassVar[int]
bundle_version: int
tensors: _containers.RepeatedCompositeFieldContainer[NamedTensor]
def __init__(self, bundle_version: _Optional[int] = ..., tensors: _Optional[_Iterable[_Union[NamedTensor, _Mapping]]] = ...) -> None: ...
class Fingerprint(_message.Message):
__slots__ = ("model_artifact_digest", "runtime_recipe_digest", "recipe_id", "recipe_version", "catalogue_version")
MODEL_ARTIFACT_DIGEST_FIELD_NUMBER: _ClassVar[int]
RUNTIME_RECIPE_DIGEST_FIELD_NUMBER: _ClassVar[int]
RECIPE_ID_FIELD_NUMBER: _ClassVar[int]
RECIPE_VERSION_FIELD_NUMBER: _ClassVar[int]
CATALOGUE_VERSION_FIELD_NUMBER: _ClassVar[int]
model_artifact_digest: str
runtime_recipe_digest: str
recipe_id: str
recipe_version: str
catalogue_version: str
def __init__(self, model_artifact_digest: _Optional[str] = ..., runtime_recipe_digest: _Optional[str] = ..., recipe_id: _Optional[str] = ..., recipe_version: _Optional[str] = ..., catalogue_version: _Optional[str] = ...) -> None: ...
class ShardRange(_message.Message):
__slots__ = ("start_layer", "end_layer", "effective_start_layer")
START_LAYER_FIELD_NUMBER: _ClassVar[int]
END_LAYER_FIELD_NUMBER: _ClassVar[int]
EFFECTIVE_START_LAYER_FIELD_NUMBER: _ClassVar[int]
start_layer: int
end_layer: int
effective_start_layer: int
def __init__(self, start_layer: _Optional[int] = ..., end_layer: _Optional[int] = ..., effective_start_layer: _Optional[int] = ...) -> None: ...
class PositionSpan(_message.Message):
__slots__ = ("first_position", "token_count")
FIRST_POSITION_FIELD_NUMBER: _ClassVar[int]
TOKEN_COUNT_FIELD_NUMBER: _ClassVar[int]
first_position: int
token_count: int
def __init__(self, first_position: _Optional[int] = ..., token_count: _Optional[int] = ...) -> None: ...
class ChunkInfo(_message.Message):
__slots__ = ("chunk_index", "chunk_count", "final_chunk")
CHUNK_INDEX_FIELD_NUMBER: _ClassVar[int]
CHUNK_COUNT_FIELD_NUMBER: _ClassVar[int]
FINAL_CHUNK_FIELD_NUMBER: _ClassVar[int]
chunk_index: int
chunk_count: int
final_chunk: bool
def __init__(self, chunk_index: _Optional[int] = ..., chunk_count: _Optional[int] = ..., final_chunk: _Optional[bool] = ...) -> None: ...
class CacheExpectation(_message.Message):
__slots__ = ("mode", "expected_past_len")
MODE_FIELD_NUMBER: _ClassVar[int]
EXPECTED_PAST_LEN_FIELD_NUMBER: _ClassVar[int]
mode: CacheMode
expected_past_len: int
def __init__(self, mode: _Optional[_Union[CacheMode, str]] = ..., expected_past_len: _Optional[int] = ...) -> None: ...
class CacheResult(_message.Message):
__slots__ = ("mode", "past_len", "cache_hit")
MODE_FIELD_NUMBER: _ClassVar[int]
PAST_LEN_FIELD_NUMBER: _ClassVar[int]
CACHE_HIT_FIELD_NUMBER: _ClassVar[int]
mode: CacheMode
past_len: int
cache_hit: bool
def __init__(self, mode: _Optional[_Union[CacheMode, str]] = ..., past_len: _Optional[int] = ..., cache_hit: _Optional[bool] = ...) -> None: ...
class Envelope(_message.Message):
__slots__ = ("schema_version", "work_id", "route_session_id", "route_epoch", "fingerprint", "shard_range", "phase", "position", "idempotency_step", "cache_expectation", "deadline_unix_nanos", "chunk")
SCHEMA_VERSION_FIELD_NUMBER: _ClassVar[int]
WORK_ID_FIELD_NUMBER: _ClassVar[int]
ROUTE_SESSION_ID_FIELD_NUMBER: _ClassVar[int]
ROUTE_EPOCH_FIELD_NUMBER: _ClassVar[int]
FINGERPRINT_FIELD_NUMBER: _ClassVar[int]
SHARD_RANGE_FIELD_NUMBER: _ClassVar[int]
PHASE_FIELD_NUMBER: _ClassVar[int]
POSITION_FIELD_NUMBER: _ClassVar[int]
IDEMPOTENCY_STEP_FIELD_NUMBER: _ClassVar[int]
CACHE_EXPECTATION_FIELD_NUMBER: _ClassVar[int]
DEADLINE_UNIX_NANOS_FIELD_NUMBER: _ClassVar[int]
CHUNK_FIELD_NUMBER: _ClassVar[int]
schema_version: SchemaVersion
work_id: str
route_session_id: str
route_epoch: int
fingerprint: Fingerprint
shard_range: ShardRange
phase: Phase
position: PositionSpan
idempotency_step: int
cache_expectation: CacheExpectation
deadline_unix_nanos: int
chunk: ChunkInfo
def __init__(self, schema_version: _Optional[_Union[SchemaVersion, str]] = ..., work_id: _Optional[str] = ..., route_session_id: _Optional[str] = ..., route_epoch: _Optional[int] = ..., fingerprint: _Optional[_Union[Fingerprint, _Mapping]] = ..., shard_range: _Optional[_Union[ShardRange, _Mapping]] = ..., phase: _Optional[_Union[Phase, str]] = ..., position: _Optional[_Union[PositionSpan, _Mapping]] = ..., idempotency_step: _Optional[int] = ..., cache_expectation: _Optional[_Union[CacheExpectation, _Mapping]] = ..., deadline_unix_nanos: _Optional[int] = ..., chunk: _Optional[_Union[ChunkInfo, _Mapping]] = ...) -> None: ...
class ShardError(_message.Message):
__slots__ = ("code", "detail", "retryable", "actual_past_len")
CODE_FIELD_NUMBER: _ClassVar[int]
DETAIL_FIELD_NUMBER: _ClassVar[int]
RETRYABLE_FIELD_NUMBER: _ClassVar[int]
ACTUAL_PAST_LEN_FIELD_NUMBER: _ClassVar[int]
code: ErrorCode
detail: str
retryable: bool
actual_past_len: int
def __init__(self, code: _Optional[_Union[ErrorCode, str]] = ..., detail: _Optional[str] = ..., retryable: _Optional[bool] = ..., actual_past_len: _Optional[int] = ...) -> None: ...
class FlowControl(_message.Message):
__slots__ = ("credits_granted", "max_inflight_chunks", "max_chunk_bytes", "max_prefill_chunk_tokens")
CREDITS_GRANTED_FIELD_NUMBER: _ClassVar[int]
MAX_INFLIGHT_CHUNKS_FIELD_NUMBER: _ClassVar[int]
MAX_CHUNK_BYTES_FIELD_NUMBER: _ClassVar[int]
MAX_PREFILL_CHUNK_TOKENS_FIELD_NUMBER: _ClassVar[int]
credits_granted: int
max_inflight_chunks: int
max_chunk_bytes: int
max_prefill_chunk_tokens: int
def __init__(self, credits_granted: _Optional[int] = ..., max_inflight_chunks: _Optional[int] = ..., max_chunk_bytes: _Optional[int] = ..., max_prefill_chunk_tokens: _Optional[int] = ...) -> None: ...
class SessionOpen(_message.Message):
__slots__ = ("schema_version", "route_session_id", "route_epoch", "fingerprint", "shard_range", "proposed_flow_control", "accepted_compression")
SCHEMA_VERSION_FIELD_NUMBER: _ClassVar[int]
ROUTE_SESSION_ID_FIELD_NUMBER: _ClassVar[int]
ROUTE_EPOCH_FIELD_NUMBER: _ClassVar[int]
FINGERPRINT_FIELD_NUMBER: _ClassVar[int]
SHARD_RANGE_FIELD_NUMBER: _ClassVar[int]
PROPOSED_FLOW_CONTROL_FIELD_NUMBER: _ClassVar[int]
ACCEPTED_COMPRESSION_FIELD_NUMBER: _ClassVar[int]
schema_version: SchemaVersion
route_session_id: str
route_epoch: int
fingerprint: Fingerprint
shard_range: ShardRange
proposed_flow_control: FlowControl
accepted_compression: _containers.RepeatedScalarFieldContainer[Compression]
def __init__(self, schema_version: _Optional[_Union[SchemaVersion, str]] = ..., route_session_id: _Optional[str] = ..., route_epoch: _Optional[int] = ..., fingerprint: _Optional[_Union[Fingerprint, _Mapping]] = ..., shard_range: _Optional[_Union[ShardRange, _Mapping]] = ..., proposed_flow_control: _Optional[_Union[FlowControl, _Mapping]] = ..., accepted_compression: _Optional[_Iterable[_Union[Compression, str]]] = ...) -> None: ...
class SessionAccepted(_message.Message):
__slots__ = ("schema_version", "route_session_id", "route_epoch", "flow_control", "accepted_compression", "fingerprint")
SCHEMA_VERSION_FIELD_NUMBER: _ClassVar[int]
ROUTE_SESSION_ID_FIELD_NUMBER: _ClassVar[int]
ROUTE_EPOCH_FIELD_NUMBER: _ClassVar[int]
FLOW_CONTROL_FIELD_NUMBER: _ClassVar[int]
ACCEPTED_COMPRESSION_FIELD_NUMBER: _ClassVar[int]
FINGERPRINT_FIELD_NUMBER: _ClassVar[int]
schema_version: SchemaVersion
route_session_id: str
route_epoch: int
flow_control: FlowControl
accepted_compression: _containers.RepeatedScalarFieldContainer[Compression]
fingerprint: Fingerprint
def __init__(self, schema_version: _Optional[_Union[SchemaVersion, str]] = ..., route_session_id: _Optional[str] = ..., route_epoch: _Optional[int] = ..., flow_control: _Optional[_Union[FlowControl, _Mapping]] = ..., accepted_compression: _Optional[_Iterable[_Union[Compression, str]]] = ..., fingerprint: _Optional[_Union[Fingerprint, _Mapping]] = ...) -> None: ...
class ActivationChunk(_message.Message):
__slots__ = ("envelope", "bundle")
ENVELOPE_FIELD_NUMBER: _ClassVar[int]
BUNDLE_FIELD_NUMBER: _ClassVar[int]
envelope: Envelope
bundle: TensorBundle
def __init__(self, envelope: _Optional[_Union[Envelope, _Mapping]] = ..., bundle: _Optional[_Union[TensorBundle, _Mapping]] = ...) -> None: ...
class DecodeStep(_message.Message):
__slots__ = ("idempotency_step", "position", "expected_past_len", "tensor", "work_id", "deadline_unix_nanos")
IDEMPOTENCY_STEP_FIELD_NUMBER: _ClassVar[int]
POSITION_FIELD_NUMBER: _ClassVar[int]
EXPECTED_PAST_LEN_FIELD_NUMBER: _ClassVar[int]
TENSOR_FIELD_NUMBER: _ClassVar[int]
WORK_ID_FIELD_NUMBER: _ClassVar[int]
DEADLINE_UNIX_NANOS_FIELD_NUMBER: _ClassVar[int]
idempotency_step: int
position: int
expected_past_len: int
tensor: NamedTensor
work_id: str
deadline_unix_nanos: int
def __init__(self, idempotency_step: _Optional[int] = ..., position: _Optional[int] = ..., expected_past_len: _Optional[int] = ..., tensor: _Optional[_Union[NamedTensor, _Mapping]] = ..., work_id: _Optional[str] = ..., deadline_unix_nanos: _Optional[int] = ...) -> None: ...
class ReleaseSignal(_message.Message):
__slots__ = ("route_session_id", "route_epoch", "work_id")
ROUTE_SESSION_ID_FIELD_NUMBER: _ClassVar[int]
ROUTE_EPOCH_FIELD_NUMBER: _ClassVar[int]
WORK_ID_FIELD_NUMBER: _ClassVar[int]
route_session_id: str
route_epoch: int
work_id: str
def __init__(self, route_session_id: _Optional[str] = ..., route_epoch: _Optional[int] = ..., work_id: _Optional[str] = ...) -> None: ...
class CancelSignal(_message.Message):
__slots__ = ("route_session_id", "route_epoch", "work_id", "reason")
ROUTE_SESSION_ID_FIELD_NUMBER: _ClassVar[int]
ROUTE_EPOCH_FIELD_NUMBER: _ClassVar[int]
WORK_ID_FIELD_NUMBER: _ClassVar[int]
REASON_FIELD_NUMBER: _ClassVar[int]
route_session_id: str
route_epoch: int
work_id: str
reason: str
def __init__(self, route_session_id: _Optional[str] = ..., route_epoch: _Optional[int] = ..., work_id: _Optional[str] = ..., reason: _Optional[str] = ...) -> None: ...
class Ack(_message.Message):
__slots__ = ("work_id", "idempotency_step", "cache_result", "duplicate", "execution_nanos")
WORK_ID_FIELD_NUMBER: _ClassVar[int]
IDEMPOTENCY_STEP_FIELD_NUMBER: _ClassVar[int]
CACHE_RESULT_FIELD_NUMBER: _ClassVar[int]
DUPLICATE_FIELD_NUMBER: _ClassVar[int]
EXECUTION_NANOS_FIELD_NUMBER: _ClassVar[int]
work_id: str
idempotency_step: int
cache_result: CacheResult
duplicate: bool
execution_nanos: int
def __init__(self, work_id: _Optional[str] = ..., idempotency_step: _Optional[int] = ..., cache_result: _Optional[_Union[CacheResult, _Mapping]] = ..., duplicate: _Optional[bool] = ..., execution_nanos: _Optional[int] = ...) -> None: ...
class ShardStatus(_message.Message):
__slots__ = ("work_id", "route_session_id", "idempotency_step", "error", "terminal")
WORK_ID_FIELD_NUMBER: _ClassVar[int]
ROUTE_SESSION_ID_FIELD_NUMBER: _ClassVar[int]
IDEMPOTENCY_STEP_FIELD_NUMBER: _ClassVar[int]
ERROR_FIELD_NUMBER: _ClassVar[int]
TERMINAL_FIELD_NUMBER: _ClassVar[int]
work_id: str
route_session_id: str
idempotency_step: int
error: ShardError
terminal: bool
def __init__(self, work_id: _Optional[str] = ..., route_session_id: _Optional[str] = ..., idempotency_step: _Optional[int] = ..., error: _Optional[_Union[ShardError, _Mapping]] = ..., terminal: _Optional[bool] = ...) -> None: ...
class SessionRequest(_message.Message):
__slots__ = ("open", "chunk", "decode", "flow_control", "release", "cancel")
OPEN_FIELD_NUMBER: _ClassVar[int]
CHUNK_FIELD_NUMBER: _ClassVar[int]
DECODE_FIELD_NUMBER: _ClassVar[int]
FLOW_CONTROL_FIELD_NUMBER: _ClassVar[int]
RELEASE_FIELD_NUMBER: _ClassVar[int]
CANCEL_FIELD_NUMBER: _ClassVar[int]
open: SessionOpen
chunk: ActivationChunk
decode: DecodeStep
flow_control: FlowControl
release: ReleaseSignal
cancel: CancelSignal
def __init__(self, open: _Optional[_Union[SessionOpen, _Mapping]] = ..., chunk: _Optional[_Union[ActivationChunk, _Mapping]] = ..., decode: _Optional[_Union[DecodeStep, _Mapping]] = ..., flow_control: _Optional[_Union[FlowControl, _Mapping]] = ..., release: _Optional[_Union[ReleaseSignal, _Mapping]] = ..., cancel: _Optional[_Union[CancelSignal, _Mapping]] = ...) -> None: ...
class SessionResponse(_message.Message):
__slots__ = ("accepted", "chunk", "ack", "flow_control", "status")
ACCEPTED_FIELD_NUMBER: _ClassVar[int]
CHUNK_FIELD_NUMBER: _ClassVar[int]
ACK_FIELD_NUMBER: _ClassVar[int]
FLOW_CONTROL_FIELD_NUMBER: _ClassVar[int]
STATUS_FIELD_NUMBER: _ClassVar[int]
accepted: SessionAccepted
chunk: ActivationChunk
ack: Ack
flow_control: FlowControl
status: ShardStatus
def __init__(self, accepted: _Optional[_Union[SessionAccepted, _Mapping]] = ..., chunk: _Optional[_Union[ActivationChunk, _Mapping]] = ..., ack: _Optional[_Union[Ack, _Mapping]] = ..., flow_control: _Optional[_Union[FlowControl, _Mapping]] = ..., status: _Optional[_Union[ShardStatus, _Mapping]] = ...) -> None: ...
class CapabilityRequest(_message.Message):
__slots__ = ("schema_version",)
SCHEMA_VERSION_FIELD_NUMBER: _ClassVar[int]
schema_version: SchemaVersion
def __init__(self, schema_version: _Optional[_Union[SchemaVersion, str]] = ...) -> None: ...
class CapabilityReport(_message.Message):
__slots__ = ("schema_version", "fingerprint", "shard_range", "backend", "device", "validated", "detail", "max_concurrent_sessions", "max_context_tokens", "flow_control", "accepted_compression", "supported_schema_versions", "validated_at_unix_nanos")
SCHEMA_VERSION_FIELD_NUMBER: _ClassVar[int]
FINGERPRINT_FIELD_NUMBER: _ClassVar[int]
SHARD_RANGE_FIELD_NUMBER: _ClassVar[int]
BACKEND_FIELD_NUMBER: _ClassVar[int]
DEVICE_FIELD_NUMBER: _ClassVar[int]
VALIDATED_FIELD_NUMBER: _ClassVar[int]
DETAIL_FIELD_NUMBER: _ClassVar[int]
MAX_CONCURRENT_SESSIONS_FIELD_NUMBER: _ClassVar[int]
MAX_CONTEXT_TOKENS_FIELD_NUMBER: _ClassVar[int]
FLOW_CONTROL_FIELD_NUMBER: _ClassVar[int]
ACCEPTED_COMPRESSION_FIELD_NUMBER: _ClassVar[int]
SUPPORTED_SCHEMA_VERSIONS_FIELD_NUMBER: _ClassVar[int]
VALIDATED_AT_UNIX_NANOS_FIELD_NUMBER: _ClassVar[int]
schema_version: SchemaVersion
fingerprint: Fingerprint
shard_range: ShardRange
backend: str
device: str
validated: bool
detail: str
max_concurrent_sessions: int
max_context_tokens: int
flow_control: FlowControl
accepted_compression: _containers.RepeatedScalarFieldContainer[Compression]
supported_schema_versions: _containers.RepeatedScalarFieldContainer[SchemaVersion]
validated_at_unix_nanos: int
def __init__(self, schema_version: _Optional[_Union[SchemaVersion, str]] = ..., fingerprint: _Optional[_Union[Fingerprint, _Mapping]] = ..., shard_range: _Optional[_Union[ShardRange, _Mapping]] = ..., backend: _Optional[str] = ..., device: _Optional[str] = ..., validated: _Optional[bool] = ..., detail: _Optional[str] = ..., max_concurrent_sessions: _Optional[int] = ..., max_context_tokens: _Optional[int] = ..., flow_control: _Optional[_Union[FlowControl, _Mapping]] = ..., accepted_compression: _Optional[_Iterable[_Union[Compression, str]]] = ..., supported_schema_versions: _Optional[_Iterable[_Union[SchemaVersion, str]]] = ..., validated_at_unix_nanos: _Optional[int] = ...) -> None: ...
class HealthRequest(_message.Message):
__slots__ = ("schema_version",)
SCHEMA_VERSION_FIELD_NUMBER: _ClassVar[int]
schema_version: SchemaVersion
def __init__(self, schema_version: _Optional[_Union[SchemaVersion, str]] = ...) -> None: ...
class HealthReport(_message.Message):
__slots__ = ("schema_version", "state", "active_sessions", "queued_chunks", "batch_occupancy", "kv_pressure", "resident_bytes", "detail")
SCHEMA_VERSION_FIELD_NUMBER: _ClassVar[int]
STATE_FIELD_NUMBER: _ClassVar[int]
ACTIVE_SESSIONS_FIELD_NUMBER: _ClassVar[int]
QUEUED_CHUNKS_FIELD_NUMBER: _ClassVar[int]
BATCH_OCCUPANCY_FIELD_NUMBER: _ClassVar[int]
KV_PRESSURE_FIELD_NUMBER: _ClassVar[int]
RESIDENT_BYTES_FIELD_NUMBER: _ClassVar[int]
DETAIL_FIELD_NUMBER: _ClassVar[int]
schema_version: SchemaVersion
state: ServingState
active_sessions: int
queued_chunks: int
batch_occupancy: int
kv_pressure: float
resident_bytes: int
detail: str
def __init__(self, schema_version: _Optional[_Union[SchemaVersion, str]] = ..., state: _Optional[_Union[ServingState, str]] = ..., active_sessions: _Optional[int] = ..., queued_chunks: _Optional[int] = ..., batch_occupancy: _Optional[int] = ..., kv_pressure: _Optional[float] = ..., resident_bytes: _Optional[int] = ..., detail: _Optional[str] = ...) -> None: ...
class ReleaseRequest(_message.Message):
__slots__ = ("schema_version", "route_session_id", "route_epoch")
SCHEMA_VERSION_FIELD_NUMBER: _ClassVar[int]
ROUTE_SESSION_ID_FIELD_NUMBER: _ClassVar[int]
ROUTE_EPOCH_FIELD_NUMBER: _ClassVar[int]
schema_version: SchemaVersion
route_session_id: str
route_epoch: int
def __init__(self, schema_version: _Optional[_Union[SchemaVersion, str]] = ..., route_session_id: _Optional[str] = ..., route_epoch: _Optional[int] = ...) -> None: ...
class ReleaseResponse(_message.Message):
__slots__ = ("released", "error")
RELEASED_FIELD_NUMBER: _ClassVar[int]
ERROR_FIELD_NUMBER: _ClassVar[int]
released: bool
error: ShardError
def __init__(self, released: _Optional[bool] = ..., error: _Optional[_Union[ShardError, _Mapping]] = ...) -> None: ...
class CancelRequest(_message.Message):
__slots__ = ("schema_version", "route_session_id", "route_epoch", "work_id", "reason")
SCHEMA_VERSION_FIELD_NUMBER: _ClassVar[int]
ROUTE_SESSION_ID_FIELD_NUMBER: _ClassVar[int]
ROUTE_EPOCH_FIELD_NUMBER: _ClassVar[int]
WORK_ID_FIELD_NUMBER: _ClassVar[int]
REASON_FIELD_NUMBER: _ClassVar[int]
schema_version: SchemaVersion
route_session_id: str
route_epoch: int
work_id: str
reason: str
def __init__(self, schema_version: _Optional[_Union[SchemaVersion, str]] = ..., route_session_id: _Optional[str] = ..., route_epoch: _Optional[int] = ..., work_id: _Optional[str] = ..., reason: _Optional[str] = ...) -> None: ...
class CancelResponse(_message.Message):
__slots__ = ("cancelled_work_items", "error")
CANCELLED_WORK_ITEMS_FIELD_NUMBER: _ClassVar[int]
ERROR_FIELD_NUMBER: _ClassVar[int]
cancelled_work_items: int
error: ShardError
def __init__(self, cancelled_work_items: _Optional[int] = ..., error: _Optional[_Union[ShardError, _Mapping]] = ...) -> None: ...

View File

@@ -0,0 +1,295 @@
# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
"""Client and server classes corresponding to protobuf-defined services."""
import grpc
import warnings
from . import shard_runtime_pb2 as shard__runtime__pb2
GRPC_GENERATED_VERSION = '1.82.1'
GRPC_VERSION = grpc.__version__
_version_not_supported = False
try:
from grpc._utilities import first_version_is_lower
_version_not_supported = first_version_is_lower(GRPC_VERSION, GRPC_GENERATED_VERSION)
except ImportError:
_version_not_supported = True
if _version_not_supported:
raise RuntimeError(
f'The grpc package installed is at version {GRPC_VERSION},'
+ ' but the generated code in shard_runtime_pb2_grpc.py depends on'
+ f' grpcio>={GRPC_GENERATED_VERSION}.'
+ f' Please upgrade your grpc module to grpcio>={GRPC_GENERATED_VERSION}'
+ f' or downgrade your generated code using grpcio-tools<={GRPC_VERSION}.'
)
class ShardRuntimeStub:
"""---------------------------------------------------------------------------
Service
---------------------------------------------------------------------------
"""
def __init__(self, channel):
"""Constructor.
Args:
channel: A grpc.Channel.
"""
self.GetCapability = channel.unary_unary(
'/meshnet.shard.v1.ShardRuntime/GetCapability',
request_serializer=shard__runtime__pb2.CapabilityRequest.SerializeToString,
response_deserializer=shard__runtime__pb2.CapabilityReport.FromString,
_registered_method=True)
self.Health = channel.unary_unary(
'/meshnet.shard.v1.ShardRuntime/Health',
request_serializer=shard__runtime__pb2.HealthRequest.SerializeToString,
response_deserializer=shard__runtime__pb2.HealthReport.FromString,
_registered_method=True)
self.Session = channel.stream_stream(
'/meshnet.shard.v1.ShardRuntime/Session',
request_serializer=shard__runtime__pb2.SessionRequest.SerializeToString,
response_deserializer=shard__runtime__pb2.SessionResponse.FromString,
_registered_method=True)
self.Release = channel.unary_unary(
'/meshnet.shard.v1.ShardRuntime/Release',
request_serializer=shard__runtime__pb2.ReleaseRequest.SerializeToString,
response_deserializer=shard__runtime__pb2.ReleaseResponse.FromString,
_registered_method=True)
self.Cancel = channel.unary_unary(
'/meshnet.shard.v1.ShardRuntime/Cancel',
request_serializer=shard__runtime__pb2.CancelRequest.SerializeToString,
response_deserializer=shard__runtime__pb2.CancelResponse.FromString,
_registered_method=True)
class ShardRuntimeServicer:
"""---------------------------------------------------------------------------
Service
---------------------------------------------------------------------------
"""
def GetCapability(self, request, context):
"""What this worker can execute. Read before a route is built.
"""
context.set_code(grpc.StatusCode.UNIMPLEMENTED)
context.set_details('Method not implemented!')
raise NotImplementedError('Method not implemented!')
def Health(self, request, context):
"""Live load and serving state.
"""
context.set_code(grpc.StatusCode.UNIMPLEMENTED)
context.set_details('Method not implemented!')
raise NotImplementedError('Method not implemented!')
def Session(self, request_iterator, context):
"""One long-lived bidirectional stream per Route Session Activation Seam.
The stream opens with SessionOpen/SessionAccepted, then carries bounded
prefill chunks and decode steps in both directions for the life of the
session. Per-token channel creation is a non-goal: the handshake cost is
paid once and the hot path carries only what changes.
"""
context.set_code(grpc.StatusCode.UNIMPLEMENTED)
context.set_details('Method not implemented!')
raise NotImplementedError('Method not implemented!')
def Release(self, request, context):
"""Drop session state out of band. Idempotent.
"""
context.set_code(grpc.StatusCode.UNIMPLEMENTED)
context.set_details('Method not implemented!')
raise NotImplementedError('Method not implemented!')
def Cancel(self, request, context):
"""Cancel out of band, on a fresh call.
In-band CancelSignal is preferred, but a sender that is blocked on flow
control cannot write one — a cancel that can only travel down a wedged
stream is not a cancel. This RPC always has a path to the worker.
"""
context.set_code(grpc.StatusCode.UNIMPLEMENTED)
context.set_details('Method not implemented!')
raise NotImplementedError('Method not implemented!')
def add_ShardRuntimeServicer_to_server(servicer, server):
rpc_method_handlers = {
'GetCapability': grpc.unary_unary_rpc_method_handler(
servicer.GetCapability,
request_deserializer=shard__runtime__pb2.CapabilityRequest.FromString,
response_serializer=shard__runtime__pb2.CapabilityReport.SerializeToString,
),
'Health': grpc.unary_unary_rpc_method_handler(
servicer.Health,
request_deserializer=shard__runtime__pb2.HealthRequest.FromString,
response_serializer=shard__runtime__pb2.HealthReport.SerializeToString,
),
'Session': grpc.stream_stream_rpc_method_handler(
servicer.Session,
request_deserializer=shard__runtime__pb2.SessionRequest.FromString,
response_serializer=shard__runtime__pb2.SessionResponse.SerializeToString,
),
'Release': grpc.unary_unary_rpc_method_handler(
servicer.Release,
request_deserializer=shard__runtime__pb2.ReleaseRequest.FromString,
response_serializer=shard__runtime__pb2.ReleaseResponse.SerializeToString,
),
'Cancel': grpc.unary_unary_rpc_method_handler(
servicer.Cancel,
request_deserializer=shard__runtime__pb2.CancelRequest.FromString,
response_serializer=shard__runtime__pb2.CancelResponse.SerializeToString,
),
}
generic_handler = grpc.method_handlers_generic_handler(
'meshnet.shard.v1.ShardRuntime', rpc_method_handlers)
server.add_generic_rpc_handlers((generic_handler,))
server.add_registered_method_handlers('meshnet.shard.v1.ShardRuntime', rpc_method_handlers)
# This class is part of an EXPERIMENTAL API.
class ShardRuntime:
"""---------------------------------------------------------------------------
Service
---------------------------------------------------------------------------
"""
@staticmethod
def GetCapability(request,
target,
options=(),
channel_credentials=None,
call_credentials=None,
insecure=False,
compression=None,
wait_for_ready=None,
timeout=None,
metadata=None):
return grpc.experimental.unary_unary(
request,
target,
'/meshnet.shard.v1.ShardRuntime/GetCapability',
shard__runtime__pb2.CapabilityRequest.SerializeToString,
shard__runtime__pb2.CapabilityReport.FromString,
options,
channel_credentials,
insecure,
call_credentials,
compression,
wait_for_ready,
timeout,
metadata,
_registered_method=True)
@staticmethod
def Health(request,
target,
options=(),
channel_credentials=None,
call_credentials=None,
insecure=False,
compression=None,
wait_for_ready=None,
timeout=None,
metadata=None):
return grpc.experimental.unary_unary(
request,
target,
'/meshnet.shard.v1.ShardRuntime/Health',
shard__runtime__pb2.HealthRequest.SerializeToString,
shard__runtime__pb2.HealthReport.FromString,
options,
channel_credentials,
insecure,
call_credentials,
compression,
wait_for_ready,
timeout,
metadata,
_registered_method=True)
@staticmethod
def Session(request_iterator,
target,
options=(),
channel_credentials=None,
call_credentials=None,
insecure=False,
compression=None,
wait_for_ready=None,
timeout=None,
metadata=None):
return grpc.experimental.stream_stream(
request_iterator,
target,
'/meshnet.shard.v1.ShardRuntime/Session',
shard__runtime__pb2.SessionRequest.SerializeToString,
shard__runtime__pb2.SessionResponse.FromString,
options,
channel_credentials,
insecure,
call_credentials,
compression,
wait_for_ready,
timeout,
metadata,
_registered_method=True)
@staticmethod
def Release(request,
target,
options=(),
channel_credentials=None,
call_credentials=None,
insecure=False,
compression=None,
wait_for_ready=None,
timeout=None,
metadata=None):
return grpc.experimental.unary_unary(
request,
target,
'/meshnet.shard.v1.ShardRuntime/Release',
shard__runtime__pb2.ReleaseRequest.SerializeToString,
shard__runtime__pb2.ReleaseResponse.FromString,
options,
channel_credentials,
insecure,
call_credentials,
compression,
wait_for_ready,
timeout,
metadata,
_registered_method=True)
@staticmethod
def Cancel(request,
target,
options=(),
channel_credentials=None,
call_credentials=None,
insecure=False,
compression=None,
wait_for_ready=None,
timeout=None,
metadata=None):
return grpc.experimental.unary_unary(
request,
target,
'/meshnet.shard.v1.ShardRuntime/Cancel',
shard__runtime__pb2.CancelRequest.SerializeToString,
shard__runtime__pb2.CancelResponse.FromString,
options,
channel_credentials,
insecure,
call_credentials,
compression,
wait_for_ready,
timeout,
metadata,
_registered_method=True)