Pinned Loading

1. djl djl Public

   Forked from deepjavalibrary/djl

   An Engine-Agnostic Deep Learning Framework in Java

   Java 1

2. cuda_pcg cuda_pcg Public

   Cuda

3. EAGLE EAGLE Public

   Forked from SafeAILab/EAGLE

   EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

   Python

4. flash-attention flash-attention Public

   Forked from Dao-AILab/flash-attention

   Fast and memory-efficient exact attention

   Python

5. qed_fermion qed_fermion Public

   Python

6. vllm-project/vllm vllm-project/vllm Public

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

   Python 55.5k 9.4k