Pinned Loading

1. lite.ai.toolkit lite.ai.toolkit Public

   🛠 A lite C++ toolkit of 100+ Awesome AI models, support ORT, MNN, NCNN, TNN and TensorRT. 🎉🎉

   C++ 3.7k 707

2. vllm-project/vllm vllm-project/vllm Public

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python 34k 5.2k

3. Awesome-LLM-Inference Awesome-LLM-Inference Public

   📖A curated list of Awesome LLM/VLM Inference Papers with codes, such as FlashAttention, PagedAttention, Parallelism, etc. 🎉🎉

   3.2k 217

4. CUDA-Learn-Notes CUDA-Learn-Notes Public

   📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

   Cuda 2k 207

5. Awesome-Diffusion-Inference Awesome-Diffusion-Inference Public

   📖A curated list of Awesome Diffusion Inference Papers with codes, such as Sampling, Caching, Multi-GPUs, etc. 🎉🎉

   169 10

6. ffpa-attn-mma ffpa-attn-mma Public

   📚[WIP] FFPA: Yet antother Faster Flash Prefill Attention with O(1)⚡️GPU SRAM complexity for headdim > 256, 1.8x~3x↑🎉faster vs SDPA EA.

   Cuda 52 1