samsja / muon_fsdp_2Links
Muon fsdp 2
☆44Updated 2 months ago
Alternatives and similar repositories for muon_fsdp_2
Users that are interested in muon_fsdp_2 are comparing it to the libraries listed below
Sorting:
- The evaluation framework for training-free sparse attention in LLMs☆101Updated last week
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆69Updated last year
- ☆86Updated last year
- Here we will test various linear attention designs.☆61Updated last year
- ☆121Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated 11 months ago
- ☆83Updated last year
- ☆53Updated last year
- Fast and memory-efficient exact attention☆71Updated 7 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆195Updated 4 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 10 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆91Updated 3 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆78Updated last year
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year
- ☆130Updated 4 months ago
- ☆55Updated 4 months ago
- Some preliminary explorations of Mamba's context scaling.☆216Updated last year
- DPO, but faster 🚀☆45Updated 10 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆129Updated last year
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- ☆52Updated 11 months ago
- A toolkit for scaling law research ⚖☆52Updated 8 months ago
- ☆91Updated last year
- Sparse Backpropagation for Mixture-of-Expert Training☆29Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆241Updated 4 months ago
- Stick-breaking attention☆61Updated 3 months ago
- ☆48Updated last year
- ☆107Updated last year
- ☆14Updated 3 months ago