Jeffery (Zeyu) Zhao

您好， 请问尝试过COCO上训练吗？能不能达到https://github.com/AlexeyAB/darknet 上的mAP？

Onnxruntime backend error when workload is high since Triton uses CUDA 12

9

**Description** When workload is high, some model in Triton ONNXRUNTIME backend will fail. And after it fails, it will never succeed again. Failures will look like: ``` "[StatusCode.INTERNAL] onnx runtime...

**Description** `memory.enable_memory_arena_shrinkage` in ONNXRuntime backend does **not** release all arena after each run. After some research, I found `session.use_device_allocator_for_initializers` might need to be `1` in order to make arena shrinkage...

能否添加一个指令允许我截取屏幕上的位置并存放至指定文件夹。这样我把事件录制好后，可以直接改脚本文件添加一些关键事件后的截屏，方便回来的时候看是不是脚本按预期执行了

Use AES CBC

4

Although not likely, randomly generated iv can be same and using same iv + key to encrypt two messages using GCM, attacker can get xor of the raw data. It's...

Does ensemble model release CUDA cache?

6

**Description** A clear and concise description of what the bug is. We set cache cleaning args on all models running on GPU. After calling them individually repeatedly, the GPU RAM...

### Is this a new feature, an improvement, or a change to existing functionality? New Feature ### How would you describe the priority of this feature request Should have (e.g....

# Rate Limiter Deadlock Fix ## Problem Description The original rate limiter implementation in Triton had a deadlock issue when using BLS calls with rate limiting enabled. The deadlock occurred...

Support Pytorch AOTInductor

2

**Is your feature request related to a problem? Please describe.** Current Pytorch backend uses libtorch, for which Pytorch community no longer actively develop / maintain. Experimental 2.0 backend uses python,...