RulinShao / LightSeqLinks
Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training
☆208Updated 9 months ago
Alternatives and similar repositories for LightSeq
Users that are interested in LightSeq are comparing it to the libraries listed below
Sorting:
- PyTorch bindings for CUTLASS grouped GEMM.☆122Updated 5 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆203Updated 2 weeks ago
- ☆105Updated 9 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆93Updated last month
- Triton-based implementation of Sparse Mixture of Experts.☆216Updated 6 months ago
- ☆248Updated last year
- ☆83Updated 3 years ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆305Updated 11 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆291Updated 6 months ago
- Zero Bubble Pipeline Parallelism☆395Updated 3 weeks ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 5 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆211Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆202Updated 6 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆196Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.☆271Updated 11 months ago
- Applied AI experiments and examples for PyTorch☆271Updated this week
- ☆73Updated 4 years ago
- Odysseus: Playground of LLM Sequence Parallelism☆69Updated 11 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆355Updated 9 months ago
- ☆118Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆506Updated last week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆75Updated 8 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆186Updated 3 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆251Updated 7 months ago
- ☆129Updated 3 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 10 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆86Updated 2 years ago
- 16-fold memory access reduction with nearly no loss☆94Updated 2 months ago
- nnScaler: Compiling DNN models for Parallel Training☆113Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆106Updated 2 months ago