yanring / Megatron-MoE-ModelZooLinks
Best practices for testing advanced Mixtral, DeepSeek, and Qwen series MoE models using Megatron Core MoE.
☆41Updated last week
Alternatives and similar repositories for Megatron-MoE-ModelZoo
Users that are interested in Megatron-MoE-ModelZoo are comparing it to the libraries listed below
Sorting:
- PyTorch bindings for CUTLASS grouped GEMM.☆107Updated 2 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆212Updated 11 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆230Updated 8 months ago
- ☆123Updated 2 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆72Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆134Updated 3 weeks ago
- ☆107Updated 11 months ago
- Estimate MFU for DeepSeekV3☆25Updated 7 months ago
- ☆85Updated 9 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆137Updated 5 months ago
- A Quirky Assortment of CuTe Kernels☆388Updated this week
- TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators☆70Updated last month
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 11 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆199Updated this week
- Applied AI experiments and examples for PyTorch☆289Updated 2 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆216Updated last year
- ☆75Updated 4 years ago
- 16-fold memory access reduction with nearly no loss☆103Updated 4 months ago
- ☆37Updated 2 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆275Updated last year
- ☆78Updated 3 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆123Updated 8 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆124Updated 2 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆206Updated last week
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆42Updated last month
- ☆50Updated 2 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆79Updated last week
- A simple calculation for LLM MFU.☆42Updated 5 months ago
- ☆60Updated 3 months ago