Nikolay

RuntimeError: CUDA error: named symbol not found CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

1

I tried to execute the following code: ```python from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer import torch model_name = "IlyaGusev/saiga_llama3_8b" quantization_config = TorchAoConfig("int4_weight_only", group_size=128) quantized_model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cuda", quantization_config=quantization_config) tokenizer =...

```python def make_relative_move(self, move: Moves, pan_offset=0.1, tilt_offset=0.1, zoom_offset=0.1): """ Perform a relative move based on the specified move type. :param move: The type of move (from Moves enum). :param pan_offset:...