Pinned Repositories
algorithm-pattern
算法模板，最科学的刷题方式，最快速的刷题路径，你值得拥有~
conv-float
with opencl realize conv
fastapi_tritonserver
grpc_demo
InternVL2-4B-OV
MeloTTS-OV
Using OpenVINO to speed up MeloTTS inference
moondream2-ov
Using OpenVINO to speed up moondream2 inference
python-call-C-API
tensorflow
An Open Source Machine Learning Framework for Everyone
TTS-OV
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
zhaohb's Repositories
zhaohb/fastapi_tritonserver
zhaohb/MeloTTS-OV
Using OpenVINO to speed up MeloTTS inference
zhaohb/moondream2-ov
Using OpenVINO to speed up moondream2 inference
zhaohb/TTS-OV
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
zhaohb/AMX-TMUL-Code-Samples
Code samples related to Intel(R) AMX
zhaohb/benchmark
A microbenchmark support library
zhaohb/ChatLM-mini-Chinese
中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调。
zhaohb/CUDA-Learn-Notes
🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
zhaohb/detr
End-to-End Object Detection with Transformers
zhaohb/Dreambooth-Stable-Diffusion
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
zhaohb/how-to-optimize-gemm
zhaohb/How_to_optimize_in_GPU
This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.
zhaohb/hpc-learning
hpc-learning
zhaohb/kernl
Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.
zhaohb/KuiperInfer
带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step
zhaohb/lectures
Material for cuda-mode lectures
zhaohb/lihang-code
《统计学习方法》的代码实现
zhaohb/llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
zhaohb/llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
zhaohb/LLM-System-Requirements
Open-source calculator for LLM system requirements.
zhaohb/mimalloc
mimalloc is a compact general purpose allocator with excellent performance.
zhaohb/my_openvino
zhaohb/myopenvino
zhaohb/openvino
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
zhaohb/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
zhaohb/q-diffusion
[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.
zhaohb/step_into_chatgpt
[昇思MindSpore技术公开课]系列第一讲：大模型专题
zhaohb/trt2023
zhaohb/xFasterTransformer
zhaohb/zhaohb