feifeibear / Odysseus-TransformerLinks
Odysseus: Playground of LLM Sequence Parallelism
☆78Updated 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:
- ☆130Updated 5 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 4 months ago
- Quantized Attention on GPU☆44Updated 11 months ago
- ☆106Updated 5 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆51Updated last year
- ☆50Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆126Updated 5 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆217Updated last year
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆75Updated 2 months ago
- ☆120Updated 2 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆244Updated 3 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- 16-fold memory access reduction with nearly no loss☆106Updated 7 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆152Updated last month
- ☆79Updated 6 months ago
- Utility scripts for PyTorch (e.g. Make Perfetto show some disappearing kernels, Memory profiler that understands more low-level allocatio…☆64Updated 2 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- ☆83Updated 9 months ago
- Vocabulary Parallelism☆24Updated 8 months ago
- ☆112Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆206Updated 4 months ago
- ☆147Updated 8 months ago
- ☆65Updated 6 months ago
- ☆72Updated 2 weeks ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆147Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆85Updated last year
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆98Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆169Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆130Updated 11 months ago
- Training library for Megatron-based models☆174Updated this week