Neo

What circumstances should low_latency_mode be set to false

9

When initializing the buffer, I need to pass in low_latency_mode. If it is true, low_latency mode is enabled. However, I found that in almost all cases, the performance of setting...

[Bug]: QwenImage offline inference crash On 5090

7

### Your current environment I used 4*5090 to test QwenImage by examples/offline_inference/qwen_image/text_to_image.py it will crash with EOFError, btw it occasionally exit with no error / warning log this is my...