shawntan / scattermoeLinks
Triton-based implementation of Sparse Mixture of Experts.
☆219Updated 6 months ago
Alternatives and similar repositories for scattermoe
Users that are interested in scattermoe are comparing it to the libraries listed below
Sorting:
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 10 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆99Updated 3 weeks ago
- ☆105Updated 9 months ago
- ☆130Updated 4 months ago
- This repository contains the experimental PyTorch native float8 training UX☆224Updated 10 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆253Updated this week
- ring-attention experiments☆144Updated 8 months ago
- 🔥 A minimal training framework for scaling FLA models☆170Updated last week
- Collection of kernels written in Triton language☆128Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 11 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆137Updated 10 months ago
- Fast low-bit matmul kernels in Triton☆322Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆79Updated 9 months ago
- Applied AI experiments and examples for PyTorch☆277Updated 3 weeks ago
- ☆114Updated 3 weeks ago
- ☆147Updated 2 years ago
- Fast and memory-efficient exact attention☆68Updated 3 months ago
- Explorations into some recent techniques surrounding speculative decoding☆269Updated 6 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆122Updated 4 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆204Updated 6 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆295Updated 7 months ago
- ☆157Updated last year
- ☆63Updated this week
- ☆254Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆310Updated 11 months ago
- Cataloging released Triton kernels.☆236Updated 5 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆358Updated 10 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆136Updated this week
- ☆108Updated last year
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆204Updated this week