sekstini / basedxlLinks
☆18Updated last year
Alternatives and similar repositories for basedxl
Users that are interested in basedxl are comparing it to the libraries listed below
Sorting:
- BFloat16 Fused Adam Operator for PyTorch☆16Updated last year
- [WIP] Better (FP8) attention for Hopper☆32Updated 10 months ago
- ☆65Updated 9 months ago
- ☆19Updated last month
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- ☆50Updated last year
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- GoldFinch and other hybrid transformer components☆45Updated last year
- ☆18Updated last year
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆42Updated 2 years ago
- RWKV-7: Surpassing GPT☆103Updated last year
- DPO, but faster 🚀☆46Updated last year
- QuIP quantization☆61Updated last year
- implementation of https://arxiv.org/pdf/2312.09299☆21Updated last year
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 8 months ago
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆18Updated last year
- A repository for research on medium sized language models.☆77Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆131Updated last year
- Writing FLUX in Triton☆41Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- Focused on fast experimentation and simplicity☆79Updated last year
- JAX Scalify: end-to-end scaled arithmetics☆18Updated last year
- Collection of autoregressive model implementation☆85Updated this week
- Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs☆110Updated 2 years ago
- Repository for CPU Kernel Generation for LLM Inference☆27Updated 2 years ago
- ☆27Updated last year
- Simple high-throughput inference library☆155Updated 8 months ago
- Work in progress.☆77Updated last month
- ☆114Updated last week
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆35Updated 10 months ago