Codekiller-Li
Follow
Stars
Xiaomi Home Integration for Home Assistant
The official GitHub mirror of the Chromium source
The Triton TensorRT-LLM Backend
📖A curated list of Awesome LLM/VLM Inference Papers with codes, such as FlashAttention, PagedAttention, Parallelism, etc. 🎉🎉
we want to create a repo to illustrate usage of transformers in chinese
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud.
Large Language Model Text Generation Inference
Universal LLM Deployment Engine with ML Compilation
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
Ongoing research training transformer models at scale
SGLang is a fast serving framework for large language models and vision language models.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
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 efficie…
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Open standard for machine learning interoperability
《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀