flashinfer-ai / flashinferLinks
FlashInfer: Kernel Library for LLM Serving
☆4,136Updated this week
Alternatives and similar repositories for flashinfer
Users that are interested in flashinfer are comparing it to the libraries listed below
Sorting:
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,296Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆4,054Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆2,954Updated last week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,753Updated last week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,362Updated 4 months ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆1,973Updated last week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,317Updated last week
- Tile primitives for speedy kernels☆2,955Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,766Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,251Updated 2 weeks ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,182Updated 3 months ago
- A throughput-oriented high-performance serving framework for LLMs☆918Updated last month
- A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. …☆1,578Updated this week
- Fast, Flexible and Portable Structured Generation☆1,396Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆5,580Updated this week
- slime is an LLM post-training framework for RL Scaling.☆2,612Updated this week
- 🚀 Efficient implementations of state-of-the-art linear attention models☆3,937Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,276Updated 6 months ago
- Minimalistic large language model 3D-parallelism training☆2,334Updated last week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,562Updated last year
- Expert Parallelism Load Balancer☆1,315Updated 8 months ago
- PyTorch native quantization and sparsity for training and inference☆2,531Updated last week
- Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs☆893Updated this week
- My learning notes/codes for ML SYS.☆4,272Updated last week
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,884Updated 8 months ago
- The Triton TensorRT-LLM Backend☆910Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆954Updated last year
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,842Updated 2 weeks ago
- how to optimize some algorithm in cuda.☆2,650Updated this week
- Puzzles for learning Triton☆2,143Updated last year