biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[torch.compile] limit inductor threads and lazy import quant (#10482)

Browse Source 
Signed-off-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
youkaichao
2024-11-20 18:36:33 -08:00
committed by GitHub
parent 2f77b6cfec
commit 388ee3de66
11 changed files with 178 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/models/internvl.py
View File

@@ -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)