DeepSpeed-MII
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed. (by microsoft)
whisper-rs
Rust bindings to https://github.com/ggerganov/whisper.cpp (by tazz4843)
Our great sponsors
DeepSpeed-MII | whisper-rs | |
---|---|---|
6 | 2 | |
1,629 | 576 | |
7.0% | - | |
8.7 | 8.5 | |
6 days ago | 5 days ago | |
Python | Rust | |
Apache License 2.0 | The Unlicense |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
DeepSpeed-MII
Posts with mentions or reviews of DeepSpeed-MII.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-12-22.
- Stable Diffusion plus DeepSpeed
-
[D] When chatGPT stops being free: Run SOTA LLM in cloud
Microsoft/DeepSpeed-MII for an up 40x reduction on inference cost on Azure, this thing also supports int8 and fp16 bloom out of the box, but it fails on Azure due to instance size.
- Image Creation Time for each GPU.
-
Anyone tried DeepSpeed-MII with stablediffusion?
Haven't tried it yet but they have some example code here: https://github.com/microsoft/DeepSpeed-MII/blob/main/examples/local/txt2img-example.py
- [P] Pure C/C++ port of OpenAI's Whisper
whisper-rs
Posts with mentions or reviews of whisper-rs.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-10-10.
-
extract audio/speech as plain text (such as CC) from a video file (.MP4, .MOV)
You might want to look at whisper-rs which are bindings to whisper.cpp: https://github.com/tazz4843/whisper-rs.
- [P] Pure C/C++ port of OpenAI's Whisper
What are some alternatives?
When comparing DeepSpeed-MII and whisper-rs you can also consider the following projects:
whisper.cpp - Port of OpenAI's Whisper model in C/C++
AITemplate - AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
petals - 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
XNNPACK - High-efficiency floating-point neural network inference operators for mobile, server, and Web
xformers - Hackable and optimized Transformers building blocks, supporting a composable construction.
HIP-CPU - An implementation of HIP that works on CPUs, across OSes.
rocm-gfx803
whisper - Robust Speech Recognition via Large-Scale Weak Supervision