exploring-AI-optimization
tvm
| exploring-AI-optimization | tvm | |
|---|---|---|
| 22 | 16 | |
| 109 | 11,244 | |
| 0.0% | 1.8% | |
| 3.8 | 9.9 | |
| 7 months ago | 2 days ago | |
| Python | ||
| MIT License | Apache License 2.0 |
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.
exploring-AI-optimization
- Collection of material on optimizing deep learning models
- Collection of material on optimization techniques for neural networks
- Collection of resources on quantization
-
[P] Open source that takes as input a deep learning model and outputs a version that runs faster in inference. Now faster and easier to use (New release)
[1] Quantization. Techniques and Concept Map. [2] Pruning. Techniques and Concept Map. [3] ONNX Runtime [4] Nvidia TensorRT [5] Intel OpenVINO [6] Apache TVM
-
Accelerating AI models online discussion
https://github.com/nebuly-ai/learning-AI-optimization/blob/main/Pruning.md here you have open source collection of material on the topic :)
- What is pruning a neural network? A guide on github. Feedback is welcome!
-
[P] Concept maps and research material on artificial intelligence optimization techniques (pruning and quantization). A guide on GitHub
Quantization github maps
tvm
-
Show HN: I built a free in-browser Llama 3 chatbot powered by WebGPU
Yes. Web-llm is a wrapper of tvmjs: https://github.com/apache/tvm
Just wrappers all the way down
-
Making AMD GPUs competitive for LLM inference
Yes, this is coming! Myself and others at OctoML and in the TVM community are actively working on multi-gpu support in the compiler and runtime. Here are some of the merged and active PRs on the multi-GPU (multi-device) roadmap:
Support in TVM’s graph IR (Relax) - https://github.com/apache/tvm/pull/15447
-
VSL; Vlang's Scientific Library
Would it make sense to have a backend support for OpenXLA, Apache TVM, Jittor or other similar to get free GPU, TPU and other accelerators for free ?
- Apache TVM
-
MLC LLM - "MLC LLM is a universal solution that allows any language model to be deployed natively on a diverse set of hardware backends and native applications, plus a productive framework for everyone to further optimize model performance for their own use cases."
I have tried the iPhone app. It's fast. They're using Apache TVM which should allow better use of native accelerators on different devices. Like using metal on Apple and Vulcan or CUDA or whatever instead of just running the thing on the CPU like llama.cpp.
-
ONNX Runtime merges WebGPU back end
I was going to answer the same, I find the approach of machine learning compilers that directly compile models to host and device code better than having to bring a huge runtime. There are exciting projects in this area like TVM Unity, IREE [2], or torch.export [3]
[1] https://github.com/apache/tvm/tree/unity
[2] https://pytorch.org/get-started/pytorch-2.0/#inference-and-e...
[3] https://pytorch.org/get-started/pytorch-2.0/#inference-and-e...
-
Esp32 tensorflow lite
Apache TVM home page: https://tvm.apache.org/
-
Decompiling x86 Deep Neural Network Executables
It's pretty clear its referring to the output of Apache TVM and Meta's Glow
-
Run Stable Diffusion on Your M1 Mac’s GPU
As mentioned in sibling comments, Torch is indeed the glue in this implementation. Other glues are TVM[0] and ONNX[1]
These just cover the neural net though, and there is lots of surrounding code and pre-/post-processing that isn't covered by these systems.
For models on Replicate, we use Docker, packaged with Cog for this stuff.[2] Unfortunately Docker doesn't run natively on Mac, so if we want to use the Mac's GPU, we can't use Docker.
I wish there was a good container system for Mac. Even better if it were something that spanned both Mac and Linux. (Not as far-fetched as it seems... I used to work at Docker and spent a bit of time looking into this...)
[0] https://tvm.apache.org/
-
How to get started with machine learning.
Or use TVM, the idea is to compile your model into code that you can load at runtime. Similar to onnxruntime, it only does DNN inference; so you need domain-specific code.
What are some alternatives?
nebuly - The user analytics platform for LLMs
TensorRT - NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
best_AI_papers_2022 - A curated list of the latest breakthroughs in AI (in 2022) by release date with a clear video explanation, link to a more in-depth article, and code.
mlc-llm - Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
awesome-ai - A curated list of artificial intelligence resources (Courses, Tools, App, Open Source Project)
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
prunnable-layers-pytorch - Prunable nn layers for pytorch.
stable-diffusion - This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements. [Moved to: https://github.com/invoke-ai/InvokeAI]
Data-science-best-resources - Carefully curated resource links for data science in one place
stable-diffusion
deepsparse - Sparsity-aware deep learning inference runtime for CPUs