Dicardo Xue's starred repositories
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
LLM-Pruner
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.
nccl-tests
NCCL Tests
kernel_tuner
Kernel Tuner
chatgpt-web
用 Express 和 Vue3 搭建的 ChatGPT 演示网页
awesome-free-chatgpt
🆓免费的 ChatGPT 镜像网站列表,持续更新。List of free ChatGPT mirror sites, continuously updated.
elasticflow-traces
Integrated Training Platform (ITP) traces used in ElasticFlow paper.
Information-Retrieval
Programming Assignments done using Python
nvidia-docker
Build and run Docker containers leveraging NVIDIA GPUs
ElasticFlow
Artifacts for our ASPLOS'23 paper ElasticFlow
HeliosArtifact
HeliosArtifact
HeliosData
Helios Traces from SenseTime
clusterdata
cluster data collected from production clusters in Alibaba for cluster management research
hivedscheduler
Kubernetes Scheduler for Deep Learning