deepreinforce-ai / CUDA-L1Links
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
☆247Updated last month
Alternatives and similar repositories for CUDA-L1
Users that are interested in CUDA-L1 are comparing it to the libraries listed below
Sorting:
- QeRL enables RL for 32B LLMs on a single H100 GPU.☆459Updated last week
- 👷 Build compute kernels☆192Updated this week
- Load compute kernels from the Hub☆348Updated this week
- Efficient LLM Inference over Long Sequences☆392Updated 5 months ago
- A collection of tricks and tools to speed up transformer models☆189Updated last month
- Simple & Scalable Pretraining for Neural Architecture Research☆304Updated last month
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated last year
- Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆194Updated this week
- ☆256Updated 6 months ago
- Work in progress.☆75Updated 2 weeks ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆320Updated last month
- FlashRNN - Fast RNN Kernels with I/O Awareness☆169Updated last month
- Quantized LLM training in pure CUDA/C++.☆220Updated last week
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆148Updated last month
- ☆111Updated 3 weeks ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆112Updated 2 months ago
- ☆219Updated 10 months ago
- Large multi-modal models (L3M) pre-training.☆222Updated 2 months ago
- The evaluation framework for training-free sparse attention in LLMs☆106Updated last month
- PyTorch implementation of models from the Zamba2 series.☆186Updated 10 months ago
- DeMo: Decoupled Momentum Optimization☆197Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆223Updated 5 months ago
- Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.☆138Updated 6 months ago
- ☆203Updated 11 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆135Updated 3 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆249Updated 10 months ago
- ☆158Updated 5 months ago
- Official repository for the paper "NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks". This rep…☆60Updated last year
- A safetensors extension to efficiently store sparse quantized tensors on disk☆214Updated this week
- Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".☆139Updated 2 weeks ago