FlashInfer: Kernel Library for LLM Serving
☆6,158Aug 13, 2026Updated this week
Alternatives and similar repositories for flashinfer
Users that are interested in flashinfer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,209Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,752Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,271Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,245Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,518Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Tile primitives for speedy kernels☆3,630Jul 13, 2026Updated last month
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,664Updated this week
- Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.☆11,760Aug 6, 2026Updated last 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…☆14,374Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,421Aug 4, 2026Updated last week
- Fast and memory-efficient exact attention☆24,701Updated 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…☆3,490Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,554Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,353Aug 28, 2025Updated 11 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Development repository for the Triton language and compiler☆19,936Updated this week
- A Quirky Assortment of CuTe Kernels☆1,107Updated this week
- My learning notes for ML SYS.☆6,864Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,223Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,743May 17, 2026Updated 2 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆7,754Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,449Jul 26, 2026Updated 2 weeks ago
- A throughput-oriented high-performance serving framework for LLMs☆974Mar 29, 2026Updated 4 months ago
- High Performance LLM Inference Operator Library☆1,108Aug 6, 2026Updated last week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,677Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,128Sep 4, 2024Updated last year
- Nano vLLM☆14,996Apr 26, 2026Updated 3 months ago
- Efficient Triton Kernels for LLM Training☆6,568Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆88,970Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,189Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆739Jul 4, 2026Updated last month
- Material for gpu-mode lectures☆6,433Jun 15, 2026Updated last month
- how to optimize some algorithm in cuda.☆3,199Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Transformer related optimization, including BERT, GPT☆6,445Mar 27, 2024Updated 2 years ago
- Materials for learning SGLang☆871Jan 5, 2026Updated 7 months ago
- slime is an LLM post-training framework for RL Scaling.☆7,885Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆3,669Updated this week
- Kernels, of the mega variety :)☆803May 26, 2026Updated 2 months ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,500Feb 20, 2026Updated 5 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆1,982Updated this week