-
Hi, @u39kun!
Nvidia claims 6x performance improvement with recent cudnn 7.2 (https://developer.nvidia.com/cudnn)
Could you please try it on Titan V?
![image](https://user-images.githubuserconte…
-
### *Project idea 6: JAX support in DocArray v2*
| Info | details |
| ---------------- | ------------------------------------------- |
| Skills ne…
-
## 🚀 Feature
Accelerate PyTorch just-in-time compilation using MKL-DNN
## Motivation
PyTorch's just-in-time (JIT) compiler rewrites and runs Pytorch model at production-efficiency. MKL-DNN is bu…
-
### Checklist
- [X] I have searched related issues but cannot get the expected help.
- [X] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/faq.md) bu…
-
* [pop media introduces OCT](
https://tw.news.yahoo.com/%E7%9C%BC%E7%A7%91%E6%AA%A2%E6%9F%A5%E5%88%A9%E5%99%A8%E3%80%8Coct%E3%80%8D%E8%A7%A3%E6%9E%90%E5%BA%A6%E8%B6%85%E9%AB%98%E3%80%80%E6%8F%AA%E5%8…
-
Hello!
I'm trying to run DeepFM with a custom subsample of the MIND dataset.
My files are:
-mind_small15.inter
-mind_small15.itememb
-mind_small15.useremb
I have very limited computing power…
-
#15 のような感じ = 機械学習最適化JITコンパイラの工夫について書いてある、#15より進んでいるのかな
高コストな融合をするか、融合をしないで大量のカーネルを出すかというジレンマがある(ジャストインタイム制約があるので)
AStichという最適化コンパイラを作った、Tensorflowから使うらしい。
Stitchは、4つのオペレータステッチングスキームを体系的に抽象化し、…
-
Einops allows the use of _rearrange_ to concatenate a list of tensors, like shown in the [einops for deep learning](https://github.com/arogozhnikov/einops/blob/master/docs/2-einops-for-deep-learning.i…
-
To make these models useful for serving we should have some export support.
-
More of a feature request than a problem report and forgive my ignorance if this is irrelevant but the nvidia 20x series and the 1660ti have tensor cores which could be use when called out on the nvid…