fla-org / flash-linear-attentionLinks
🚀 Efficient implementations of state-of-the-art linear attention models
☆4,209Updated this week
Alternatives and similar repositories for flash-linear-attention
Users that are interested in flash-linear-attention are comparing it to the libraries listed below
Sorting:
- Muon is an optimizer for hidden layers in neural networks☆2,179Updated last month
- A PyTorch native platform for training generative AI models☆4,947Updated this week
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆952Updated 9 months ago
- Tile primitives for speedy kernels☆3,038Updated this week
- Helpful tools and examples for working with flex-attention☆1,105Updated this week
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper☆791Updated 4 months ago
- Official PyTorch implementation for "Large Language Diffusion Models"☆3,459Updated 2 months ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,939Updated 4 months ago
- Muon is Scalable for LLM Training☆1,397Updated 5 months ago
- Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States☆1,300Updated last year
- Puzzles for learning Triton☆2,222Updated last year
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,065Updated this week
- FlashInfer: Kernel Library for LLM Serving☆4,438Updated 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…☆3,055Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,611Updated this week
- Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch☆1,864Updated this week
- Minimalistic large language model 3D-parallelism training☆2,407Updated last month
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,637Updated last year
- slime is an LLM post-training framework for RL Scaling.☆3,224Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆4,417Updated last week
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,729Updated 8 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,410Updated 5 months ago
- NanoGPT (124M) in 3 minutes☆4,116Updated this week
- A collection of AWESOME things about mixture-of-experts☆1,253Updated last year
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,030Updated 9 months ago
- Scalable toolkit for efficient model reinforcement☆1,210Updated this week
- [TMLR 2024] Efficient Large Language Models: A Survey☆1,247Updated 6 months ago
- Official Repo for Open-Reasoner-Zero☆2,085Updated 7 months ago
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,071Updated 3 weeks ago
- A curated list for Efficient Large Language Models☆1,925Updated 6 months ago