feifeibear / Odysseus-TransformerLinks
Odysseus: Playground of LLM Sequence Parallelism
☆79Updated 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:
- ☆133Updated 7 months ago
- ☆117Updated 7 months ago
- Quantized Attention on GPU☆44Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 6 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆139Updated 7 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆53Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆220Updated last year
- ☆52Updated 7 months ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆43Updated last month
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆256Updated 5 months ago
- ☆115Updated last year
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆160Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Updated 3 months ago
- ☆84Updated 8 months ago
- Triton implementation of Flash Attention2.0☆47Updated 2 years ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆90Updated last year
- Vocabulary Parallelism☆24Updated 10 months ago
- Distributed IO-aware Attention algorithm☆23Updated 3 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated 2 years ago
- Low-bit optimizers for PyTorch☆137Updated 2 years ago
- Triton-based implementation of Sparse Mixture of Experts.☆259Updated 3 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆112Updated 2 months ago
- ☆156Updated 10 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆175Updated last year
- ☆85Updated 11 months ago
- ☆126Updated 4 months ago
- ☆216Updated last month
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆98Updated 4 months ago