LiuXiaoxuanPKU

LiuXiaoxuanPKU's Stars

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++74.3k5714.5k10.7k

• vllm-project/vllm

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

  Language:Python39.3k3246.7k5.9k

• karpathy/llm.c

  LLM training in simple, raw C/CUDA

  Language:Cuda25.8k2641453k

• plasma-umass/scalene

  Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

  Language:Python12.5k90480405

• srush/GPU-Puzzles

  Solve puzzles. Learn CUDA.

  Language:Jupyter Notebook10.5k13333820

• SkalskiP/courses

  This repository is a curated collection of links to various courses and resources about Artificial Intelligence (AI)

  Language:Python5.6k947519

• DefTruth/Awesome-LLM-Inference

  📖A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, Flash-Attention, Paged-Attention, Parallelism, etc. 🎉🎉

  3.5k1126239

• Zjh-819/LLMDataHub

  A quick guide (especially) for trending instruction finetuning datasets

  2.9k503185

• huggingface/blog

  Public repo for HF blog posts

  Language:Jupyter Notebook2.7k95264828

• FranxYao/chain-of-thought-hub

  Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

  Language:Jupyter Notebook2.7k3934132

• FasterDecoding/Medusa

  Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

  Language:Jupyter Notebook2.4k3092168

• flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Language:Cuda2.2k26213224

• microsoft/DeepSpeed-MII

  MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

  Language:Python2k42315176

• huachaohuang/awesome-dbdev

  Awesome materials about database development.

  1.5k48079

• the-full-stack/website

  Source for https://fullstackdeeplearning.com

  Language:HTML1.2k3231207

• kakaobrain/torchgpipe

  A GPipe implementation in PyTorch

  Language:Python829333498

• THUDM/LongBench

  LongBench v2 and LongBench (ACL 2024)

  Language:Python78579974

• mirage-project/mirage

  Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA

  Language:C++748176844

• hemingkx/SpeculativeDecodingPapers

  📰 Must-read papers and blogs on Speculative Decoding ⚡️

  59828428

• apoorvumang/prompt-lookup-decoding

  Language:Jupyter Notebook50411624

• rmihaylov/falcontune

  Tune any FALCON in 4-bit

  Language:Python466123552

• bojone/NBCE

  Naive Bayes-based Context Extension

  Language:Python3206722

• lucidrains/speculative-decoding

  Explorations into some recent techniques surrounding speculative decoding

  Language:Python24110519

• amesar/mlflow-examples

  Basic and advanced MLflow examples for many ML flavors

  Language:Python21861879

• HPMLL/BurstGPT

  A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems

  Language:Python147649

• r2e-project/r2e

  r2e: turn any github repository into a programming agent environment

  Language:Python1003311

• EmbeddedLLM/vllm-rocm

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

  Language:Python872135

• tyler-griggs/melange-release

  Language:Python43205

• vllm-project/dashboard

  vLLM performance dashboard

  Language:Python20105

• flashinfer-ai/debug-print

  Debug print operator for cudagraph debugging

  Language:Cuda10100