flashinfer-ai / flashinfer
FlashInfer: Kernel Library for LLM Serving
☆2,659Updated this week
Alternatives and similar repositories for flashinfer:
Users that are interested in flashinfer are comparing it to the libraries listed below
- A throughput-oriented high-performance serving framework for LLMs☆794Updated 6 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,355Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,922Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,213Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,169Updated this week
- Tile primitives for speedy kernels☆2,251Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,122Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆971Updated this week
- Minimalistic large language model 3D-parallelism training☆1,786Updated this week
- Redis for LLMs☆753Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,077Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆864Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆797Updated 7 months ago
- 📚A curated list of Awesome LLM/VLM🔥 Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, MLA, Parallelism etc.☆3,817Updated this week
- Fast, Flexible and Portable Structured Generation☆865Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,037Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,383Updated 9 months ago
- The Triton TensorRT-LLM Backend☆819Updated last week
- [NeurIPS'24 Spotlight, ICLR'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which r…☆969Updated last week
- A PyTorch Native LLM Training Framework☆783Updated 3 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,783Updated last week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,236Updated last month
- Serving multiple LoRA finetuned LLM as one☆1,052Updated 11 months ago
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆798Updated this week
- 🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton☆2,250Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆635Updated last month
- PyTorch native quantization and sparsity for training and inference☆1,954Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,999Updated 3 weeks ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆774Updated 3 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,489Updated 9 months ago