foricee

foricee's Stars

• IST-DASLab/marlin

  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

  Language:Python56145

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++65.1k9.3k

• sony/ctm

  Language:Python21711

• leffff/adversarial-diffusion-distillation

  My Implementation of Adversarial Diffusion Distillation https://arxiv.org/pdf/2311.17042.pdf

  Language:Jupyter Notebook383

• ExponentialML/Text-To-Video-Finetuning

  Finetune ModelScope's Text To Video model using Diffusers 🧨

  Language:Python657104

• bnabis93/vision-language-examples

  Vision-lanugage model example code.

  Language:Python8

• alibaba/rtp-llm

  RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

  Language:C++51348

• siboehm/SGEMM_CUDA

  Fast CUDA matrix multiplication from scratch

  Language:Cuda42255

• wangsiping97/FastGEMV

  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.

  Language:Cuda813

• alibaba/animate-anything

  Fine-Grained Open Domain Image Animation with Motion Guidance

  Language:Python71859

• openmlsys/openmlsys-zh

  《Machine Learning Systems: Design and Implementation》- Chinese Version

  Language:TeX4k430

• triton-inference-server/tensorrtllm_backend

  The Triton TensorRT-LLM Backend

  Language:Python65493

• NVIDIA/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.

  Language:C++8.2k910

• facebookresearch/xformers

  Hackable and optimized Transformers building blocks, supporting a composable construction.

  Language:Python8.4k588

• triton-lang/triton

  Development repository for the Triton language and compiler

  Language:C++12.7k1.5k

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python13.4k1.2k

• karpathy/ng-video-lecture

  Language:Python3.4k890

• InternLM/lmdeploy

  LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

  Language:Python4.2k378

• NVIDIA/FasterTransformer

  Transformer related optimization, including BERT, GPT

  Language:C++5.8k882

• HqWu-HITCS/Awesome-Chinese-LLM

  整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

  14.9k1.4k

• benbalter/word-to-markdown

  A ruby gem to liberate content from Microsoft Word documents

  Language:Ruby1.5k156

• HIT-SCIR-SC/QiaoBan

  Language:Python17119

• wilmerwang/autoLiterature

  autoLiterature是一个基于Python的自动文献管理命令行工具

  Language:Python35551

• NaiboWang/EasySpider

  A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。

  Language:JavaScript34.3k4.2k

• ai-shifu/ChatALL

  Concurrently chat with ChatGPT, Bing Chat, Bard, Alpaca, Vicuna, Claude, ChatGLM, MOSS, 讯飞星火, 文心一言 and more, discover the best answers

  Language:JavaScript15.1k1.6k

• PolyAI-LDN/conversational-datasets

  Large datasets for conversational AI

  Language:Python1.3k166

• yanqiangmiffy/InstructGLM

  ChatGLM-6B 指令学习|指令数据|Instruct

  Language:Python65551

• wenda-LLM/wenda

  闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题

  Language:JavaScript6.2k810

• linjinjin123/awesome-AIOps

  AIOps学习资料汇总，欢迎一起补全这个仓库，欢迎star

  1.5k357

• microsoft/JARVIS

  JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

  Language:Python23.5k2k