[Quantization][TPU] compressed-tensors
integration for TPU
#23606
Annotations
6 errors
|
Analysing the code with ruff:
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py#L4
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py:4:8: F401 `torch_xla` imported but unused
|
Analysing the code with ruff:
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py#L5
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py:5:36: F401 `torch_xla.core.xla_model` imported but unused
|
Analysing the code with ruff:
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py#L40
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py:40:81: E501 Line too long (84 > 80)
|
Analysing the code with ruff:
vllm/worker/tpu_worker.py#L131
vllm/worker/tpu_worker.py:131:81: E501 Line too long (82 > 80)
|
Analysing the code with ruff
Process completed with exit code 1.
|
Loading