-
I got an error
```
TracerArrayConversionError: The numpy.ndarray conversion method __array__() was called on traced array with shape float64[].
The error occurred while tracing the function generi…
-
## Overview
As MXNet development approaches its 2.0 major milestone, we would like to update our community on roadmap status, and highlight new and upcoming features.
### Motivation
The deep …
-
## 🐛 Bug
Android Apk load llm crash, org.apache.tvm.Base$TVMError: InternalError: Check failed: type_code_ == kTVMObjectHandle (0 vs. 8) : expected Object but got int
## To Reproduce
Steps to…
-
### 请提出你的问题 Please ask your question
想问下dlpack 在完成框架间转换的时候是如何 确定stream 同步的，因为不同框架间同步的方式不同，看array api 中是有__dlpack__(steam) 来保证自己框架去做同步，pytotch 类似的实现是：https://github.com/pytorch/pytorch/blob/main/torch…
-
**Describe the bug**
Dividing two decimal columns with equal scale N results in 0 fractional digits in the output (i.e. the result is truncated). I would expect that if division returns a result of…
-
## 🐛 Bug
I've successfully compiled the Llama-3-8B-Instruct model using q4f16_1 quantization and converted it into Android compatible file (Llama-3-8B-Instruct-q4f16_1-android.tar).
Now, I'm fo…
-
Hi,
I am unable to build onnxruntime with "--build_wheel" and "--enable_pybind" options. I have confirmed that I have python 3.8 installed and all the dependencies. It compiles perfectly without t…
-
AMD has just released their port for MXnet to AMD GPUs, to be found [here](https://github.com/ROCmSoftwarePlatform/mxnet).
Please merge that code, so MXnet works on both NVidia and AMD hardware.
-
### 🐛 Describe the bug
Right now, around 1.5k files are grandfathered in as "not UFMT'ed" in the PyTorch codebase. Let's make them all formatted!
To format a file, remove its name from `exclude_…
-
**Describe the bug**
Hi, tried to install cuML on a computing cluster via conda in existing environment and then in a new environment.
I also tried the advice found here https://github.com/rapidsai/…