A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 14:45 UTC
[Bugfix][TPU] Fix TPU validate_request (#16369)
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Michael Goin committed
Apr 9, 2025 at 22:55 UTC
baada0e737430ac093cb984c63502ef509a0b7d7
1 file changed
+1
-4
vllm/platforms/tpu.py
+1
-4
@@ -7,20 +7,17 @@ import torch
7
import vllm.envs as envs
8
from vllm.inputs import PromptType
9
from vllm.logger import init_logger
10
+from vllm.sampling_params import SamplingParams
11
12
from .interface import Platform, PlatformEnum, _Backend
13
14
if TYPE_CHECKING:
15
from vllm.config import ModelConfig, VllmConfig
15
- from vllm.lora.request import LoRARequest
16
from vllm.pooling_params import PoolingParams
17
- from vllm.sampling_params import SamplingParams
17
else:
18
ModelConfig = None
19
VllmConfig = None
21
- LoRARequest = None
20
PoolingParams = None
23
- SamplingParams = None
21
22
logger = init_logger(__name__)
23