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
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- ☆19Updated 2 months ago
- [WIP] Better (FP8) attention for Hopper☆32Updated 11 months ago
- ☆50Updated last year
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 9 months ago
- ☆67Updated 10 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- ☆18Updated last year
- DPO, but faster 🚀☆47Updated last year
- RWKV-7: Surpassing GPT☆104Updated last year
- research impl of Native Sparse Attention (2502.11089)☆63Updated 11 months ago
- A repository for research on medium sized language models.☆77Updated last year
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆42Updated 2 years ago
- QuIP quantization☆61Updated last year
- Simple high-throughput inference library☆155Updated 8 months ago
- ☆34Updated last year
- ☆13Updated 2 years ago
- GoldFinch and other hybrid transformer components☆45Updated last year
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆18Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆131Updated last year
- implementation of https://arxiv.org/pdf/2312.09299☆21Updated last year
- Writing FLUX in Triton☆41Updated last year
- JAX Scalify: end-to-end scaled arithmetics☆18Updated last year
- Focused on fast experimentation and simplicity☆80Updated 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
- ☆63Updated last year
- ☆32Updated last year
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆33Updated last year
- ☆41Updated last year