There are no reviews yet. Be the first to send feedback to the community and the maintainers!
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.MQBench
Model Quantization BenchmarkUnited-Perception
United Perceptionllmc
This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".Dipoorlet
Offline Quantization Tools for Deploy.awesome-lm-system
Summary of system papers/frameworks/codes/tools on training or serving large modelTFMQ-DM
[CVPR 2024 Highlight] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models".mqbench-paper
rank_dataset
PyTorch Dataset Rank DatasetNART
NART = NART is not A RunTime, a deep learning inference framework.EasyLLM
Built upon Megatron-Deepspeed and HuggingFace Trainer, EasyLLM has reorganized the code logic with a focus on usability. While enhancing usability, it also ensures training efficiency.Outlier_Suppression_Plus
Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scalingNNLQP
QLLM
[ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models"LPCV2021_Winner_Solution
pyvlova
Yet another Polyhedra Compiler for DeepLearningLPCV_2023_solution
AAAI2023_EAMPD
AAAI2023 Efficient and Accurate Models towards Practical Deep Learning BaselinePrototype
L2_Compression
OmniBal
msbench
A tool for model sparse based on torch.fxImagenet-S
Robustness for real-world system noisemtc-token-healing
Token healing implementation in RustFCPTS
statecs
general-sam-py
Python bindings for general-sam and some utilitiespyrotom
Python Code Hotfix and Refactor on the flyLove Open Source and this site? Check out how you can help us