linkedin / Liger-KernelLinks
Efficient Triton Kernels for LLM Training
☆5,492Updated last week
Alternatives and similar repositories for Liger-Kernel
Users that are interested in Liger-Kernel are comparing it to the libraries listed below
Sorting:
- A PyTorch native platform for training generative AI models☆4,195Updated this week
- FlashInfer: Kernel Library for LLM Serving☆3,524Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,195Updated 3 weeks ago
- PyTorch native quantization and sparsity for training and inference☆2,245Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,654Updated last month
- Tile primitives for speedy kernels☆2,570Updated last week
- Puzzles for learning Triton☆1,832Updated 8 months ago
- Minimalistic large language model 3D-parallelism training☆2,121Updated last month
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,761Updated this week
- 🚀 Efficient implementations of state-of-the-art linear attention models☆3,030Updated this week
- PyTorch native post-training library☆5,399Updated this week
- NanoGPT (124M) in 3 minutes☆2,985Updated 3 weeks ago
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,585Updated 9 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,480Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,627Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,045Updated 4 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,593Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,462Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,224Updated 3 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆4,691Updated this week
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆3,353Updated 2 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆16,773Updated this week
- Material for gpu-mode lectures☆4,842Updated last month
- DataComp for Language Models☆1,347Updated last week
- TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizati…☆11,313Updated this week
- Fast, Flexible and Portable Structured Generation☆1,153Updated this week
- Tools for merging pretrained large language models.☆6,170Updated 2 weeks ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,506Updated last week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,350Updated last week
- PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily wri…☆1,384Updated this week