"vscode:/vscode.git/clone" did not exist on "d201807339697c6c8206ae08d2cdccfc25cb1ce1"
Unverified Commit 3c49dbdd authored by Yikun Jiang's avatar Yikun Jiang Committed by GitHub
Browse files

Skip device and quant Pydantic validation to make plugin device work (#18843)


Signed-off-by: default avatarYikun Jiang <yikunkero@gmail.com>
parent 1661a9c2
......@@ -304,7 +304,7 @@ class ModelConfig:
- 25.6k -> 25,600"""
spec_target_max_model_len: Optional[int] = None
"""Specify the maximum length for spec decoding draft models."""
quantization: Optional[QuantizationMethods] = None
quantization: SkipValidation[Optional[QuantizationMethods]] = None
"""Method used to quantize the weights. If `None`, we first check the
`quantization_config` attribute in the model config file. If that is
`None`, we assume the model weights are not quantized and use `dtype` to
......@@ -2231,7 +2231,7 @@ Device = Literal["auto", "cuda", "neuron", "cpu", "tpu", "xpu", "hpu"]
class DeviceConfig:
"""Configuration for the device to use for vLLM execution."""
device: Union[Device, torch.device] = "auto"
device: SkipValidation[Union[Device, torch.device]] = "auto"
"""Device type for vLLM execution.
This parameter is deprecated and will be
removed in a future release.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment