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>
72 lines
2.0 KiB
Python
72 lines
2.0 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
from dataclasses import dataclass
|
|
from typing import Any, Dict, List, Tuple
|
|
|
|
import torch
|
|
|
|
from vllm.pooling_params import PoolingParams
|
|
from vllm.utils import is_pin_memory_available
|
|
|
|
|
|
class PoolingMetadata:
|
|
"""Metadata for pooling operations in the Pooler layer.
|
|
|
|
This class holds the necessary information for pooling operations,
|
|
providing context for how to perform pooling and other related operations.
|
|
|
|
Attributes:
|
|
seq_groups: List of (seq_ids, pooling_params).
|
|
seq_data: A mapping of sequence ID to additional sequence data.
|
|
prompt_lens: List of the lengths of each prompt.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
seq_groups: List[Tuple[List[int], PoolingParams]],
|
|
seq_data: Dict[int, Any], # Specific data related to sequences
|
|
prompt_lens: List[int],
|
|
) -> None:
|
|
self.seq_groups = seq_groups
|
|
self.seq_data = seq_data
|
|
self.prompt_lens = prompt_lens
|
|
|
|
def __repr__(self) -> str:
|
|
return ("PoolingMetadata("
|
|
f"seq_groups={self.seq_groups}, "
|
|
f"seq_data={self.seq_data}, "
|
|
f"prompt_lens={self.prompt_lens})")
|
|
|
|
|
|
@dataclass
|
|
class PoolingTensors:
|
|
"""Tensors for pooling."""
|
|
|
|
prompt_lens: torch.Tensor
|
|
|
|
@classmethod
|
|
def from_pooling_metadata(
|
|
cls,
|
|
pooling_metadata: "PoolingMetadata",
|
|
device: torch.device,
|
|
) -> "PoolingTensors":
|
|
"""
|
|
Create PoolingTensors from PoolingMetadata.
|
|
|
|
Args:
|
|
pooling_metadata: PoolingMetadata instance to convert.
|
|
device: Device to store the tensors.
|
|
"""
|
|
# Convert prompt lengths to tensor
|
|
pin_memory = is_pin_memory_available()
|
|
|
|
prompt_lens_t = torch.tensor(
|
|
pooling_metadata.prompt_lens,
|
|
device="cpu",
|
|
dtype=torch.long,
|
|
pin_memory=pin_memory,
|
|
)
|
|
|
|
return cls(prompt_lens=prompt_lens_t.to(device=device,
|
|
non_blocking=True), )
|