
mixture-of-experts
by lucidrains (personal account)
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models (description from the project’s GitHub page)
Repository facts
- Stars
- 876
- Forks
- 71
- Open issues and pull requests
- 7
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- lucidrains · Personal account
- Created
- Jul 13, 2020
- Last push
- Sep 13, 2023
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 908: FareedKhan-dev/kimi-k3-in-c
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
9,094 starsCApache-2.0Last push Oct 2, 2026
Rank 9,294: brontoguana/krasis
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
522 starsC++Other licenseLast push Sep 15, 2026
Rank 5,360: The-AI-Summer/self-attention-cv
Implementation of various self-attention mechanisms focused on computer vision. Ongoing repository.
1,214 starsPythonMITLast push Sep 14, 2021
Rank 5,744: lucidrains/tab-transformer-pytorch
Implementation of TabTransformer, attention network for tabular data, in Pytorch
1,099 starsPythonMITLast push Jan 8, 2026
Rank 6,824: lucidrains/linear-attention-transformer
Transformer based on a variant of attention that is linear complexity in respect to sequence length
845 starsPythonMITLast push May 5, 2024
Rank 8,772: lucidrains/enformer-pytorch
Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch
575 starsPythonMITLast push Jun 26, 2026