Russell Bryant
e489ad7a21
- **Add SPDX license headers to python source files** - **Check for SPDX headers using pre-commit** commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745 Author: Russell Bryant <rbryant@redhat.com> Date: Fri Jan 31 14:18:24 2025 -0500 Add SPDX license headers to python source files This commit adds SPDX license headers to python source files as recommended to the project by the Linux Foundation. These headers provide a concise way that is both human and machine readable for communicating license information for each source file. It helps avoid any ambiguity about the license of the code and can also be easily used by tools to help manage license compliance. The Linux Foundation runs license scans against the codebase to help ensure we are in compliance with the licenses of the code we use, including dependencies. Having these headers in place helps that tool do its job. More information can be found on the SPDX site: - https://spdx.dev/learn/handling-license-info/ Signed-off-by: Russell Bryant <rbryant@redhat.com> commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea Author: Russell Bryant <rbryant@redhat.com> Date: Fri Jan 31 14:36:32 2025 -0500 Check for SPDX headers using pre-commit Signed-off-by: Russell Bryant <rbryant@redhat.com> --------- Signed-off-by: Russell Bryant <rbryant@redhat.com>
89 lines
2.4 KiB
Python
89 lines
2.4 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
import enum
|
|
from dataclasses import dataclass
|
|
from typing import TYPE_CHECKING, List, Optional, Union
|
|
|
|
import msgspec
|
|
|
|
from vllm.v1.metrics.stats import SchedulerStats
|
|
|
|
if TYPE_CHECKING:
|
|
from vllm.lora.request import LoRARequest
|
|
from vllm.multimodal import MultiModalKwargs
|
|
from vllm.multimodal.inputs import PlaceholderRange
|
|
from vllm.sampling_params import SamplingParams
|
|
|
|
|
|
@dataclass
|
|
class EngineCoreRequest:
|
|
|
|
# NOTE: prompt and prompt_token_ids should be DecoderOnlyInput,
|
|
# but this object is currently not playing well with msgspec
|
|
# due to circular imports and typing we have in data.py
|
|
|
|
request_id: str
|
|
# NOTE(ywang96): original text prompt is needed when a request is added to
|
|
# Detokenizer, but set to None when it is added to EngineCoreClient.
|
|
prompt: Optional[str]
|
|
prompt_token_ids: List[int]
|
|
mm_inputs: Optional[List[Optional["MultiModalKwargs"]]]
|
|
mm_hashes: Optional[List[str]]
|
|
mm_placeholders: Optional[List["PlaceholderRange"]]
|
|
sampling_params: "SamplingParams"
|
|
eos_token_id: Optional[int]
|
|
arrival_time: float
|
|
lora_request: Optional["LoRARequest"]
|
|
|
|
|
|
class EngineCoreOutput(
|
|
msgspec.Struct,
|
|
array_like=True, # type: ignore[call-arg]
|
|
omit_defaults=True, # type: ignore[call-arg]
|
|
gc=False): # type: ignore[call-arg]
|
|
|
|
request_id: str
|
|
new_token_ids: List[int]
|
|
finished: bool
|
|
finish_reason: Optional[str] = None
|
|
stop_reason: Union[int, str, None] = None
|
|
|
|
|
|
class EngineCoreOutputs(
|
|
msgspec.Struct,
|
|
array_like=True, # type: ignore[call-arg]
|
|
omit_defaults=True, # type: ignore[call-arg]
|
|
gc=False): # type: ignore[call-arg]
|
|
|
|
#NOTE(Nick): We could consider ways to make this more compact,
|
|
# e.g. columnwise layout and using an int enum for finish/stop reason
|
|
|
|
# [num_reqs]
|
|
outputs: List[EngineCoreOutput]
|
|
scheduler_stats: SchedulerStats
|
|
|
|
|
|
@dataclass
|
|
class EngineCoreProfile:
|
|
is_start: bool
|
|
|
|
|
|
@dataclass
|
|
class EngineCoreResetPrefixCache:
|
|
pass
|
|
|
|
|
|
class EngineCoreRequestType(enum.Enum):
|
|
"""
|
|
Request types defined as hex byte strings, so it can be sent over sockets
|
|
without separate encoding step.
|
|
"""
|
|
ADD = b'\x00'
|
|
ABORT = b'\x01'
|
|
PROFILE = b'\x02'
|
|
RESET_PREFIX_CACHE = b'\x03'
|
|
|
|
|
|
EngineCoreRequestUnion = Union[EngineCoreRequest, EngineCoreProfile,
|
|
EngineCoreResetPrefixCache, List[str]]
|