tf-metal-experiments
litenn
tf-metal-experiments | litenn | |
---|---|---|
5 | 4 | |
259 | 69 | |
- | - | |
0.0 | 0.0 | |
about 2 years ago | over 3 years ago | |
Jupyter Notebook | Python | |
MIT License | MIT License |
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.
tf-metal-experiments
- Launch HN: Metal (YC W23) – Embeddings as a Service
-
M2 Pro or M2 Max for AI?
My take on Apple M series SOCs: I don’t think any of them can hold a candle to Nvidia GPUs. The M2 Pro is like 1/8th of a 3090 and the M2 Max is 1/5th. https://github.com/tlkh/tf-metal-experiments
- TensorFlow Metal Back End on Apple Silicon Experiments (Just for Fun)
- [N] AMD launches MI200 AI accelerators (2.5x Nvidia A100 FP32 performance)
-
[D] How does tensorflow perform on M1 Pro/Max?
Some initial tests going on here: https://github.com/tlkh/tf-metal-experiments
litenn
- AMD GPU
- [N] AMD launches MI200 AI accelerators (2.5x Nvidia A100 FP32 performance)
-
[P] DLPrimitives - an OpenCL miro-framework and inference library
also look at architecture of my lib github.com/iperov/litenn . It has no fast GEMM, but written in pure python, IDE hint friendly, and new custom kernels can be easily added.
-
[D] Simple implementation of 2D convolution neural network (CNN)
look at https://github.com/iperov/litenn
What are some alternatives?
Transformer-Explainability - [CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
MetalPetal - A GPU accelerated image and video processing framework built on Metal.
HugsVision - HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision
adanet - Fast and flexible AutoML with learning guarantees.
ML-Workspace - 🛠 All-in-one web-based IDE specialized for machine learning and data science.
metal
MetalFilters - Instagram filters implemented in Metal
chatgpt-retrieval-plugin - The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.