-
**What do you want to do?**
- [ ] Request a change to existing documentation
- [x] Add new documentation
- [ ] Report a technical problem with the documentation
- [ ] Other
**Tell us about …
-
Self-Compressing Neural Networks is dynamic quantization-aware training that puts the size of the model in the loss
Paper: https://arxiv.org/pdf/2301.13142
Code: https://github.com/geohot/ai-noteb…
-
```
gh workflow run measure.yaml \
-f name=os-network-compression \
-f chaos=network-latency-5 \
-f helm-arguments="--set camunda-platform.zeebe.image.tag=SNAPSHOT --set camunda-platform.ze…
-
## Description
Async compression currently has a lot of overhead, due to allocating and deallocating a new `AsyncTask` object for every batch compressed. When there are a large number of packets to…
-
- https://arxiv.org/abs/1911.02497
- 2019
深層ニューラルネットワーク（DNN）は、学習したタスクに必要な量よりもはるかに多くの重みを高精度で表現していることが多い。
そのため、重みの刈り込みや量子化などの手法を用いて圧縮することで、精度を落とさずにモデルサイズと推論時間を削減できることが多い。
しかし、DNN、ハードウェアプラットフォーム、最…
e4exp updated
3 years ago
-
## CVE-2024-8508 - Medium Severity Vulnerability
Vulnerable Library - src3.1.5
MidnightBSD OS source code
Library home page: https://github.com/MidnightBSD/src.git
Found in base branch: stable/3.2…
-
Hi, when the string is long, brotli.encode/decode cuts the string in half, I've tried with several long strings and the result is the same, with short strings it works fine.
code example (I'm runni…
-
**Describe the problem you are trying to solve**
Decompression can be an bottleneck if the network is fast. XZ (LZMA) is surprising slow and can quickly dominate the time spent on installation.
…
-
**Describe the problem you have/What new integration you would like**
Add support for the `http_request` component on the host platform in ESPHome, or override / bypass the http_request check in th…
-
When I "docker push" to a private repository hosted on the local network or host, the upload process is entirely bound by the speed of compressing each layer with xz, using a single CPU.
I'd like an …