NVFP4 Emulation #59
Closed
NVFP4 Emulation #59
Annotations
9 errors
|
run_fp4.py#L15
run_fp4.py:15:81: E501 Line too long (102 > 80)
|
|
run_fp4.py#L16
run_fp4.py:16:81: E501 Line too long (104 > 80)
|
|
run_fp4.py#L17
run_fp4.py:17:81: E501 Line too long (108 > 80)
|
|
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py#L304
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py:304:81: E501 Line too long (82 > 80)
|
|
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py#L305
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py:305:9: F841 Local variable `is_group_size_16` is assigned to but never used
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py#L11
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py:11:81: E501 Line too long (81 > 80)
|
|
vllm/model_executor/layers/quantization/modelopt.py#L17
vllm/model_executor/layers/quantization/modelopt.py:17:81: E501 Line too long (81 > 80)
|
|
vllm/model_executor/layers/quantization/modelopt.py#L394
vllm/model_executor/layers/quantization/modelopt.py:394:22: F841 Local variable `group_size` is assigned to but never used
|
|
|
The logs for this run have expired and are no longer available.
Loading