zhoushenglong

@Reinerzhou · User

GitHub profile ↗ · Compare

4 followers23 repositories

Repositories

Reinerzhou/llm-action

本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地)

★ 0Forks 0

Reinerzhou/CUDA-Learn-Notes

📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

★ 0Forks 0

Reinerzhou/Awesome-LLM-Inference

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

★ 0Forks 0

Reinerzhou/LLM-Dojo

欢迎来到 LLM-Dojo,这里是一个开源大模型学习场所,使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩‍🎓👨‍🎓

★ 0Forks 0

Reinerzhou/lightseq

LightSeq: A High Performance Library for Sequence Processing and Generation

★ 0Forks 0

Reinerzhou/lmdeploy

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

★ 0PythonForks 0

Reinerzhou/mla-fuse

MLA的设计可以保证效果与传统的MHA效果相同的情况下,实现更低的kv-cache开销。但是官方并没有给出矩阵融合后的推理代码,这对于对齐论文中的效果是必要的一步。本仓库的代码用来实现MLA的参数融合,以及融合后的pytorch推理代码。

★ 0Forks 0

Reinerzhou/magic-animate

[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

★ 0Forks 0

Reinerzhou/awesome-ai-painting

AI绘画资料合集(包含国内外可使用平台、使用教程、参数教程、部署教程、业界新闻等等) Stable diffusion、AnimateDiff、Stable Cascade 、Stable SDXL Turbo

★ 0Forks 0

Reinerzhou/PULSE

PULSE: Pretrained and Unified Language Service Engine

★ 0Forks 0

Reinerzhou/lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

★ 0Forks 0

Reinerzhou/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

★ 0Forks 0

Reinerzhou/accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

★ 0Forks 0