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>
77 lines
2.4 KiB
Python
77 lines
2.4 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
"""A centralized entrypoint to perform distributed KV cache transfer.
|
|
|
|
This implementation is a shim wrapper on two APIs exposed by `kv_connector`:
|
|
1. `send_kv_caches_and_hidden_states`
|
|
2. `recv_kv_caches_and_hidden_states
|
|
"""
|
|
from typing import TYPE_CHECKING, List, Tuple, Union
|
|
|
|
if TYPE_CHECKING:
|
|
from vllm.worker.model_runner import ModelInputForGPUWithSamplingMetadata
|
|
from vllm.config import VllmConfig
|
|
|
|
import torch
|
|
|
|
from vllm.distributed.kv_transfer.kv_connector.factory import (
|
|
KVConnectorFactory)
|
|
from vllm.logger import init_logger
|
|
from vllm.sequence import IntermediateTensors
|
|
|
|
logger = init_logger(__name__)
|
|
|
|
|
|
class KVTransferAgent:
|
|
"""
|
|
A class designated for distributed KV transfer
|
|
|
|
Target use cases:
|
|
1. Disaggregated prefill
|
|
2. Remote KV cache storage
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
rank: int,
|
|
local_rank: int,
|
|
config: "VllmConfig",
|
|
):
|
|
|
|
self.config = config
|
|
|
|
if config.kv_transfer_config is None:
|
|
raise ValueError("KVTransferConfig is not set in the VllmConfig,"
|
|
" cannot initialize KVConnector.")
|
|
|
|
assert self.config.kv_transfer_config.is_kv_transfer_instance, "KV"\
|
|
"TransferAgent should only be used when kv_connector is set."
|
|
|
|
self.connector = KVConnectorFactory.create_connector(
|
|
rank, local_rank, config)
|
|
|
|
def send_kv_caches_and_hidden_states(
|
|
self,
|
|
model_executable: torch.nn.Module,
|
|
model_input: "ModelInputForGPUWithSamplingMetadata",
|
|
kv_caches: List[torch.Tensor],
|
|
hidden_or_intermediate_states: Union[torch.Tensor,
|
|
IntermediateTensors],
|
|
) -> None:
|
|
|
|
self.connector.send_kv_caches_and_hidden_states(
|
|
model_executable, model_input, kv_caches,
|
|
hidden_or_intermediate_states)
|
|
|
|
def close(self) -> None:
|
|
self.connector.close()
|
|
|
|
def recv_kv_caches_and_hidden_states(
|
|
self, model_executable: torch.nn.Module,
|
|
model_input: "ModelInputForGPUWithSamplingMetadata",
|
|
kv_caches: List[torch.Tensor]
|
|
) -> Tuple[Union[torch.Tensor, IntermediateTensors], bool,
|
|
"ModelInputForGPUWithSamplingMetadata"]:
|
|
|
|
return self.connector.recv_kv_caches_and_hidden_states(
|
|
model_executable, model_input, kv_caches)
|