linkedin / Liger-KernelLinks
Efficient Triton Kernels for LLM Training
☆5,738Updated this 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☆4,504Updated this week
- Minimalistic large language model 3D-parallelism training☆2,246Updated last month
- FlashInfer: Kernel Library for LLM Serving☆3,861Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,846Updated last month
- NanoGPT (124M) in 3 minutes☆3,176Updated 2 months ago
- PyTorch native post-training library☆5,523Updated this week
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,610Updated 11 months ago
- Tile primitives for speedy kernels☆2,803Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,073Updated this week
- Puzzles for learning Triton☆2,031Updated 10 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models☆3,484Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,634Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,392Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,289Updated 2 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,763Updated this week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,724Updated 2 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,987Updated this week
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆4,100Updated last month
- AllenAI's post-training codebase☆3,232Updated this week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,663Updated this week
- Fast, Flexible and Portable Structured Generation☆1,297Updated this week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,635Updated last year
- nanoGPT style version of Llama 3.1☆1,429Updated last year
- Implementation for MatMul-free LM.☆3,031Updated 2 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,254Updated 5 months ago
- Tools for merging pretrained large language models.☆6,352Updated 3 weeks ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,112Updated last month
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,596Updated 5 months ago
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆3,451Updated 4 months ago
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,611Updated last month