feifeibear / Odysseus-TransformerLinks
Odysseus: Playground of LLM Sequence Parallelism
☆72Updated last year
Alternatives and similar repositories for Odysseus-Transformer
Users that are interested in Odysseus-Transformer are comparing it to the libraries listed below
Sorting:
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆42Updated last month
- ☆123Updated 2 months ago
- Quantized Attention on GPU☆44Updated 8 months ago
- ☆49Updated 2 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆106Updated 2 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆212Updated 11 months ago
- ☆75Updated 2 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆149Updated last month
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆124Updated 2 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- ☆136Updated 5 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆218Updated last month
- ☆78Updated 3 months ago
- Vocabulary Parallelism☆19Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆60Updated 3 months ago
- ☆79Updated 6 months ago
- 16-fold memory access reduction with nearly no loss☆102Updated 4 months ago
- ☆107Updated 11 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
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 11 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆67Updated this week
- Distributed IO-aware Attention algorithm☆21Updated 11 months ago
- ☆92Updated 4 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated last year
- Best practices for testing advanced Mixtral, DeepSeek, and Qwen series MoE models using Megatron Core MoE.☆41Updated this week
- Transformers components but in Triton☆34Updated 2 months ago