[torch.compile] limit inductor threads and lazy import quant (#10482)
Signed-off-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
@@ -19,8 +19,8 @@ from vllm.attention import AttentionMetadata
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.inputs import (INPUT_REGISTRY, DecoderOnlyInputs, DummyData,
|
||||
InputContext, token_inputs)
|
||||
from vllm.model_executor.layers.quantization import (AWQConfig,
|
||||
QuantizationConfig)
|
||||
from vllm.model_executor.layers.quantization import QuantizationConfig
|
||||
from vllm.model_executor.layers.quantization.awq import AWQConfig
|
||||
from vllm.model_executor.layers.sampler import SamplerOutput, get_sampler
|
||||
from vllm.model_executor.models.intern_vit import (InternVisionModel,
|
||||
InternVisionPatchModel)
|
||||
|
||||
@@ -51,9 +51,10 @@ from vllm.model_executor.layers.linear import (ColumnParallelLinear,
|
||||
RowParallelLinear)
|
||||
from vllm.model_executor.layers.logits_processor import LogitsProcessor
|
||||
from vllm.model_executor.layers.pooler import Pooler, PoolingType
|
||||
from vllm.model_executor.layers.quantization import (GPTQConfig,
|
||||
GPTQMarlinConfig,
|
||||
QuantizationConfig)
|
||||
from vllm.model_executor.layers.quantization import QuantizationConfig
|
||||
from vllm.model_executor.layers.quantization.gptq import GPTQConfig
|
||||
from vllm.model_executor.layers.quantization.gptq_marlin import (
|
||||
GPTQMarlinConfig)
|
||||
from vllm.model_executor.layers.sampler import SamplerOutput, get_sampler
|
||||
from vllm.model_executor.layers.vocab_parallel_embedding import ParallelLMHead
|
||||
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
|
||||
|
||||
Reference in New Issue
Block a user