[Quantization][TPU] compressed-tensors integration for TPU
#23591
Annotations
4 errors
|
|
|
Analysing the code with ruff:
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py#L5
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py:5:22: F401 `torch.nn.Parameter` imported but unused
|
|
Analysing the code with ruff:
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py#L11
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py:11:5: F811 Redefinition of unused `QuantizationStrategy` from line 4
|
|
Analysing the code with ruff
Process completed with exit code 1.
|
Loading