nikhilvyas / SOAP_MUON
Combining SOAP and MUON
☆15Updated 2 months ago
Alternatives and similar repositories for SOAP_MUON:
Users that are interested in SOAP_MUON are comparing it to the libraries listed below
- Code for the paper "Function-Space Learning Rates"☆19Updated last week
- sigma-MoE layer☆18Updated last year
- ☆19Updated 3 weeks ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆26Updated last year
- [Oral; Neurips OPT2024 ] μLO: Compute-Efficient Meta-Generalization of Learned Optimizers☆12Updated last month
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated 10 months ago
- Efficient PScan implementation in PyTorch☆16Updated last year
- ☆26Updated 2 weeks ago
- ☆32Updated last year
- Here we will test various linear attention designs.☆60Updated last year
- ☆14Updated last month
- Official Code Repository for the paper "Key-value memory in the brain"☆24Updated 2 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆48Updated last month
- Official code for the paper "Attention as a Hypernetwork"☆28Updated 10 months ago
- Parallel Associative Scan for Language Models☆18Updated last year
- ☆47Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆37Updated last year
- [ICLR 2025] Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"☆95Updated 2 weeks ago
- ☆30Updated 5 months ago
- ☆31Updated last year
- ☆53Updated last month
- Using FlexAttention to compute attention with different masking patterns☆43Updated 7 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆55Updated 11 months ago
- Blog post☆17Updated last year
- ☆20Updated 10 months ago
- Stick-breaking attention☆52Updated last month
- Triton Implementation of HyperAttention Algorithm☆47Updated last year
- ☆27Updated last year
- research impl of Native Sparse Attention (2502.11089)☆53Updated 2 months ago
- ☆53Updated 9 months ago