-
### Prerequisites
- [X] I am running the latest code. Mention the version if possible as well.
- [X] I carefully followed the [README.md](https://github.com/ggerganov/llama.cpp/blob/master/README.md)…
-
I've been looking into the sd3 train branch, im trying to understand how are the loss gathered for multi-gpu and would love to understand the logic behind it.
I'm used to working with accelerator.gat…
-
Hi, your work is great. When I use RTX 4070 GPU, it takes about 10 minutes to generate an image, so I wonder if there are any methods that can reduce the generating time to about 10 seconds?
-
### System Info
```Shell
- `Accelerate` version: 0.32.1
- Platform: Linux-4.19.90-24.4.v2101.ky10.aarch64-aarch64-with-glibc2.28
- Python version: 3.10.9
- Numpy version: 1.26.4
- PyTorch vers…
-
I am trying to compute ephemerides from orbits with poliastro. Bluntly put, I need Cartesian coordinates in fixed time intervals for longer periods of times. poliastro can generate `Orbit` objects fro…
-
Hi, thanks for your great work!
I have a small question about KV Cache quantization. Did you use pagedattention to accelerate KV Cache 4-bit quantization? If so, where is the corresponding cuda kerne…
-
#### Your system information
* Steam client version: 1708985249
* Distribution : Arch Wayland
* Opted into Steam client beta?: Yes
* Have you checked for system updates?: Yes
* Steam Logs: [ste…
-
We should improve the enemy AI. Currently, it picks from three random actions:
- Deceleration
- Acceleration towards player
- Acceleration in random direction
The last one causes erratic behavio…
-
I hope to use TensorRT for acceleration during service deployment, but I haven't found any related work online, so I would like to ask here if the ESPnet team has any relevant experience. #TTS
-
I am trying to optimize the efficiency of my training scripts, and I found that there is a very big difference in the time of the same code (especially the data preparation and backward parts) when de…