LLM training in simple, raw C/CUDA
Repository Index
65,264 visible repositories in the index
1–4 of 4 · Most stars
FlashInfer: Kernel Library for LLM Serving
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
- attention
- inference-acceleration
- llm
- quantization
how to optimize some algorithm in cuda.