Popular repositories Loading

1. vllm vllm Public

   Forked from vllm-project/vllm

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

   Python

2. time_measurer time_measurer Public

   Python

3. apex apex Public

   Forked from ROCm/apex

   A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

   Python

4. SageAttention SageAttention Public

   Forked from thu-ml/SageAttention

   Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

   Cuda

5. flash-attention-nebius-patches flash-attention-nebius-patches Public

   Forked from vllm-project/flash-attention

   Fast and memory-efficient exact attention

   Python

6. ReportsHelper ReportsHelper Public

   HTML