flashinfer-ai / flashinferView external linksLinks
FlashInfer: Kernel Library for LLM Serving
☆4,935Feb 10, 2026Updated last week
Alternatives and similar repositories for flashinfer
Users that are interested in flashinfer are comparing it to the libraries listed below
Sorting:
- SGLang is a high-performance serving framework for large language models and multimodal models.☆23,547Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,771Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,896Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆12,867Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆945Oct 29, 2025Updated 3 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆5,191Updated this week
- Tile primitives for speedy kernels☆3,139Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,350Feb 9, 2026Updated last week
- Fast and memory-efficient exact attention☆22,231Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,266Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,018Sep 4, 2024Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,247Aug 28, 2025Updated 5 months ago
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,990Jan 18, 2026Updated 3 weeks ago
- Efficient Triton Kernels for LLM Training☆6,141Updated this week
- Development repository for the Triton language and compiler☆18,429Updated 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…☆3,163Updated this week
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,379Updated this week
- Transformer related optimization, including BERT, GPT☆6,392Mar 27, 2024Updated last year
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,606Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆812Mar 6, 2025Updated 11 months ago
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆9,666Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,175Feb 3, 2026Updated last week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,130Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆461May 30, 2025Updated 8 months ago
- Materials for learning SGLang☆743Jan 5, 2026Updated last month
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,436Jul 17, 2025Updated 6 months ago
- how to optimize some algorithm in cuda.☆2,819Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆6,095Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆70,205Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆776Apr 6, 2025Updated 10 months ago
- Serving multiple LoRA finetuned LLM as one☆1,139May 8, 2024Updated last year
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,860Updated this week
- DeepEP: an efficient expert-parallel communication library☆8,984Feb 9, 2026Updated last week
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,486Feb 6, 2026Updated last week
- My learning notes for ML SYS.☆5,351Jan 30, 2026Updated 2 weeks ago
- Material for gpu-mode lectures☆5,726Feb 1, 2026Updated 2 weeks ago
- Ongoing research training transformer models at scale☆15,213Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,182Jan 27, 2026Updated 2 weeks ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,737Updated this week