- [2026-06-10] DefTruth, Butterfingrz (2026). FFPA: Efficient Flash Prefill Attention for Large Head Dimensions via Split-D. Zenodo, 2026. 🎉🎉🎉
xlite-dev
Develop ML/AI toolkits and ML/AI/CUDA Learning resources.
Pinned Loading
Repositories
Showing 10 of 74 repositories
- ffpa-attn Public
Fast and Memory-Efficient Exact Attention (BF16/FP16/FP8/FP4) for Large Headdim, 1.5x~15x speedup over PyTorch SDPA.
- LeetCUDA Public
Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.
- sglang Public Forked from sgl-project/sglang
SGLang is a fast serving framework for large language models and vision language models.
- Awesome-LLM-Inference Public
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
-
- CuTe Public Forked from NVlabs/CuTe
Reference implementation and examples of the CuTe Layout representation and algebra.
Top languages
Loading…
Most used topics
Loading…
