RulinShao / LightSeqLinks
Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training
☆220Updated last year
Alternatives and similar repositories for LightSeq
Users that are interested in LightSeq are comparing it to the libraries listed below
Sorting:
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆147Updated 2 weeks ago
- Triton-based implementation of Sparse Mixture of Experts.☆259Updated 3 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆135Updated 7 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆178Updated 3 weeks ago
- ☆115Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆175Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆332Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆396Updated last year
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆218Updated 3 weeks ago
- ☆89Updated 3 years ago
- ☆157Updated 10 months ago
- ☆298Updated 5 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆63Updated last year
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆213Updated 3 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆79Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆112Updated 9 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆362Updated 5 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆500Updated last week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆90Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆256Updated 4 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆177Updated 2 weeks ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆214Updated 10 months ago
- ☆351Updated last year
- ☆133Updated 7 months ago
- Applied AI experiments and examples for PyTorch☆312Updated 4 months ago
- Zero Bubble Pipeline Parallelism☆444Updated 8 months ago
- Explorations into some recent techniques surrounding speculative decoding☆295Updated last year
- ☆122Updated last year