Pinned Repositories
6s965-fall2022
fast-DiT
Fast Diffusion Models with Transformers
fastllm
纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行
feixyz10.github.io
My site
network-representation-learning
network-representation-learning: DeepWalk, LINE, Node2Vec, GraRep
oh_my_loam
ROS-free implementation of LOAM
oh_my_vslam
my implementation of visual slam, it's ros-free!
ohLLM
Pure C++ LLM inference engine, support quantization, mainstream LLM models, GPUs...
postdoc-report-latex-template-zju
postdoc report latex template for Zhejiang University (ZJU)
pytorch-llm-infer
pytorch llm inference: oh my implementation (from scratch) of some famous large language model (LLM) for inference purpose only.
feixyz10's Repositories
feixyz10/oh_my_loam
ROS-free implementation of LOAM
feixyz10/network-representation-learning
network-representation-learning: DeepWalk, LINE, Node2Vec, GraRep
feixyz10/oh_my_vslam
my implementation of visual slam, it's ros-free!
feixyz10/pytorch-llm-infer
pytorch llm inference: oh my implementation (from scratch) of some famous large language model (LLM) for inference purpose only.
feixyz10/ohLLM
Pure C++ LLM inference engine, support quantization, mainstream LLM models, GPUs...
feixyz10/postdoc-report-latex-template-zju
postdoc report latex template for Zhejiang University (ZJU)
feixyz10/6s965-fall2022
feixyz10/fast-DiT
Fast Diffusion Models with Transformers
feixyz10/fastllm
纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行
feixyz10/feixyz10.github.io
My site
feixyz10/ggml
Tensor library for machine learning
feixyz10/inferflow
Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).
feixyz10/reading
feixyz10/stereonet
my implementation of StereoNet
feixyz10/yolov3-pytorch
feixyz10/TinyChatEngine
TinyChatEngine: On-Device LLM Inference Library