flashinfer-ai / flashinferLinks
FlashInfer: Kernel Library for LLM Serving
☆4,285Updated 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☆2,447Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆4,289Updated 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…☆3,007Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,436Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,795Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,004Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,389Updated 5 months ago
- Tile primitives for speedy kernels☆3,008Updated 2 weeks ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,208Updated 3 months ago
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,852Updated 3 weeks ago
- Fast, Flexible and Portable Structured Generation☆1,428Updated this week
- slime is an LLM post-training framework for RL Scaling.☆2,911Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,296Updated 7 months ago
- A throughput-oriented high-performance serving framework for LLMs☆924Updated last month
- ☆1,087Updated this week
- vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization☆2,050Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,065Updated last month
- A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresse…☆1,681Updated this week
- Minimalistic large language model 3D-parallelism training☆2,365Updated last week
- A Datacenter Scale Distributed Inference Serving Framework☆5,673Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,280Updated last week
- My learning notes for ML SYS.☆4,632Updated last week
- PyTorch native quantization and sparsity for training and inference☆2,576Updated this week
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,849Updated last week
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,089Updated this week
- how to optimize some algorithm in cuda.☆2,702Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,083Updated 5 months ago
- Expert Parallelism Load Balancer☆1,322Updated 8 months ago
- Puzzles for learning Triton☆2,187Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,577Updated last year