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:
- [WIP] Better (FP8) attention for Hopper☆32Updated 9 months ago
- BFloat16 Fused Adam Operator for PyTorch☆16Updated last year
- ☆19Updated this week
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆18Updated last year
- ☆66Updated 8 months ago
- ☆50Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- RWKV-7: Surpassing GPT☆100Updated last year
- QuIP quantization☆61Updated last year
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 7 months ago
- implementation of https://arxiv.org/pdf/2312.09299☆21Updated last year
- DPO, but faster 🚀☆46Updated last year
- Writing FLUX in Triton☆41Updated last year
- High-throughput tensor loading for PyTorch☆204Updated last week
- ☆18Updated last year
- ☆13Updated 2 years ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- GoldFinch and other hybrid transformer components☆45Updated last year
- JAX Scalify: end-to-end scaled arithmetics☆17Updated last year
- research impl of Native Sparse Attention (2502.11089)☆63Updated 9 months ago
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆41Updated 2 years ago
- ☆63Updated last year
- Focused on fast experimentation and simplicity☆75Updated 11 months ago
- PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu☆76Updated last year
- Simple high-throughput inference library☆150Updated 6 months ago
- ☆52Updated last year
- ☆78Updated 11 months ago
- Work in progress.☆75Updated last week
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated last year
- Collection of autoregressive model implementation☆85Updated 7 months ago