-
## Issue template
I am trying to read the motor encoder, calculate odometry, and send the data back to my PC at 100 Hz. Using rclc_publisher_init_default, it can publish data, but only at 13 Hz. So, …
-
We are trying to using all reduce TP to slash the communication time. I noticed that you have implemented [Row split + all_reduce for MLP (not faster, disabled)](https://github.com/turboderp/exllamav2…
-
I want something like this:
```py
import mlx.core as mx
import mlx.nn as nn
mx.metal.set_cache_limit(0)
def dload(x, *args, **kwargs):
la = mx.load(*args, **kwargs)
@mx.custom_function
…
-
## Issue template
- Hardware description: ESP32 and NEMA 17 driven with A4988 on 1/16th step mode
- Installation type: humble
#### Steps to reproduce the issue
I found that i cannot drive the …
-
Hi. I pushed gtsam into Debian, and I see (among other things) that it doesn't
build on armhf and i386. Can one of you please take a look? It'll take yall much
less time to detangle this than it wou…
-
## Description
I used C++'s Tensor and CUDA APIs to infer the RT-DETRv2 model, and during the runtime, I discovered the following issues,The output information of Tensor's API does not match. When I …
-
Hello ALL,
I tried to convert [this](https://github.com/azmathmoosa/azFace) weights and cfg files. And Even I tried to use new cfg files as mentioned in https://github.com/pjreddie/darknet/tree/ma…
-
Hi!
I'm using latest CNTK and Keras on Windows.
I'm faced with an error on Keras Conv2DTranspose as shown below.
The code works fine with TensorFlow backend. Any idea what's going on?
```…
-
Request the buffers that hold depthai output data that is available to user code to be aligned and also be allocated by the user's choice of allocator. Why?
* alignment is good. And necessary for s…
-
### 🐛 Describe the bug
`torch.linalg.eigh` crashes if the model is compiled into an AOTInductor model and used from the C++ side. The example python code is attached as follows:
```python
import os…