Tiantian-Han

3D-ResNets-PyTorch

3D ResNets for Action Recognition (CVPR 2018)

AdderNet

Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"

aimet

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

AISystem

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

alibabacloud-quantization-networks

alibabacloud-quantization-networks

AnalyticalScaleForIntegerQuantization

Example for applying Gaussian and Laplace clipping on activations of CNN.

apq

[CVPR 2020] APQ: Joint Search for Network Architecture, Pruning and Quantization Policy

arcface-pytorch

ATSS

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

ColossalAI

Making large AI models cheaper, faster and more accessible

Tiantian-Han/ColossalAI

Making large AI models cheaper, faster and more accessible

Tiantian-Han/AISystem

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Tiantian-Han/Awesome-Efficient-LLM

A curated list for Efficient Large Language Models

Tiantian-Han/bfp_quant

Tiantian-Han/bitsandbytes

8-bit CUDA functions for PyTorch

Tiantian-Han/deepsparse

Sparsity-aware deep learning inference runtime for CPUs

Tiantian-Han/Efficient-LLMs-Survey

Efficient Large Language Models: A Survey

Tiantian-Han/float8_experimental

This repository contains the experimental PyTorch native float8 training UX

Tiantian-Han/fp6_llm

An efficient GPU support for LLM inference with 6-bit quantization (FP6).

Tiantian-Han/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.

Tiantian-Han/LLM-FP4

The official implementation of the EMNLP 2023 paper LLM-FP4

Tiantian-Han/llm_interview_note

大模型面试题及答案，大模型八股文

Tiantian-Han/lm-evaluation-harness

A framework for few-shot evaluation of language models.

Tiantian-Han/LoftQ

Tiantian-Han/LSQuantization

The PyTorch implementation of Learned Step size Quantization (LSQ) in ICLR2020 (unofficial)

Tiantian-Han/Megatron-LM

Ongoing research training transformer models at scale

Tiantian-Han/microxcaling

PyTorch emulation library for Microscaling (MX)-compatible data formats

Tiantian-Han/ml_dtypes

A stand-alone implementation of several NumPy dtype extensions used in machine learning.

Tiantian-Han/nanoGPT_MXFP4

Tiantian-Han/onnx2torch

Convert ONNX models to PyTorch.

Tiantian-Han/peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Tiantian-Han/PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Tiantian-Han/qa-lora

Official PyTorch implementation of QA-LoRA

Tiantian-Han/QAQ-KVCacheQuantization

QAQ: Quality Adaptive Quantization for LLM KV Cache

Tiantian-Han/QuaRot

Code for QuaRot, an end-to-end 4-bit inference of large language models.

Tiantian-Han/serverchan-demo

Server酱多语言调用实例

Tiantian-Han/tiny-asic-4bit-matrix-mul

Tiny matrix multiplication ASIC with 4-bit math

Tiantian-Han/UltraEval

An open source framework for evaluating foundation models.

Tiantian-Han/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Tiantian-Han/what-is

Important concepts in numerical linear algebra and related areas