Skip to content

@ModelTC ModelTC

Change the repository type filter

All

    Repositories list

    43 repositories

    • lightllm

      Public
      LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
      nlpdeep-learningllamagptmodel-servingllmopenai-triton
      Python
      •
      Apache License 2.0
      •231•3k•67•7•Updated Mar 4, 2025Mar 4, 2025

    • llmc

      Public
      [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".
      benchmarkdeploymenttoolevaluationpruningquantizationpost-training-quantizationawqlarge-language-modelsllm
      Python
      •
      Apache License 2.0
      •49•422•14•1•Updated Mar 1, 2025Mar 1, 2025

    • lightllm-blog

      Public
      SCSS
      •
      MIT License
      •0•0•0•0•Updated Feb 19, 2025Feb 19, 2025

    • LLM_QAT

      Public
      Python
      •0•0•0•0•Updated Feb 19, 2025Feb 19, 2025

    • modeltc.github.io

      Public
      HTML
      •0•0•0•0•Updated Jan 25, 2025Jan 25, 2025

    • MQBench

      Public
      Model Quantization Benchmark
      Python
      •
      Apache License 2.0
      •142•789•5•5•Updated Jan 20, 2025Jan 20, 2025

    • general-sam-py

      Public
      Python bindings for general-sam and some utilities
      Python
      •
      Apache License 2.0
      •0•3•0•2•Updated Jan 13, 2025Jan 13, 2025

    • mtc-token-healing

      Public
      Token healing implementation in Rust
      Rust
      •
      Apache License 2.0
      •0•4•0•4•Updated Jan 13, 2025Jan 13, 2025

    • quant_horizon

      Public
      Cuda
      •
      Apache License 2.0
      •2•10•0•0•Updated Jan 10, 2025Jan 10, 2025

    • general-sam

      Public
      A general suffix automaton implementation in Rust with Python bindings
      Rust
      •
      Apache License 2.0
      •0•6•0•1•Updated Oct 18, 2024Oct 18, 2024

    • EasyLLM

      Public
      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.
      Python
      •
      Apache License 2.0
      •7•45•0•0•Updated Sep 18, 2024Sep 18, 2024

    • DeepSpeed

      Public
      DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
      Python
      •
      Apache License 2.0
      •4.3k•0•0•0•Updated Sep 13, 2024Sep 13, 2024

    • opencompass

      Public
      OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
      Python
      •
      Apache License 2.0
      •514•1•0•0•Updated Sep 6, 2024Sep 6, 2024

    • xtuner

      Public
      An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
      Python
      •
      Apache License 2.0
      •328•0•0•0•Updated Aug 22, 2024Aug 22, 2024

    • InternVL

      Public
      [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的可商用开源多模态对话模型
      Python
      •
      MIT License
      •549•0•0•0•Updated Aug 16, 2024Aug 16, 2024

    • OmniBal

      Public
      Python
      •1•19•2•0•Updated Aug 9, 2024Aug 9, 2024

    • TFMQ-DM

      Public
      [CVPR 2024 Highlight] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models".
      highlightquantizationcvprldmdiffusion-modelspost-training-quantizationddimstable-diffusioncvpr2024
      Jupyter Notebook
      •
      Apache License 2.0
      •4•60•0•0•Updated Aug 1, 2024Aug 1, 2024

    • L2_Compression

      Public
      Python
      •
      Apache License 2.0
      •0•13•1•0•Updated Jun 16, 2024Jun 16, 2024

    • msbench

      Public
      A tool for model sparse based on torch.fx
      Python
      •
      Apache License 2.0
      •2•8•0•0•Updated Jun 3, 2024Jun 3, 2024

    • FCPTS

      Public template
      Python
      •1•3•0•0•Updated May 14, 2024May 14, 2024

    • statecs

      Public
      Rust
      •
      Apache License 2.0
      •1•1•0•0•Updated May 10, 2024May 10, 2024

    • greedy-tokenizer

      Public
      Greedily tokenize strings with the longest tokens iteratively.
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Mar 27, 2024Mar 27, 2024

    • QLLM

      Public
      [ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models"
      transformerspytorchllamaquantizationpost-training-quantizationllmllama2
      Python
      •
      Apache License 2.0
      •4•35•2•0•Updated Mar 11, 2024Mar 11, 2024

    • Dipoorlet

      Public
      Offline Quantization Tools for Deploy.
      Python
      •
      Apache License 2.0
      •17•124•12•2•Updated Dec 28, 2023Dec 28, 2023

    • awesome-lm-system

      Public
      Summary of system papers/frameworks/codes/tools on training or serving large model
      Apache License 2.0
      •5•56•0•0•Updated Dec 17, 2023Dec 17, 2023

    • LPCV_2023_solution

      Public
      Python
      •2•18•0•0•Updated Nov 29, 2023Nov 29, 2023

    • Outlier_Suppression_Plus

      Public
      Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling
      Python
      •
      MIT License
      •4•47•0•0•Updated Oct 21, 2023Oct 21, 2023

    • UP_LPCV2023_Plugin

      Public
      Python
      •1•0•0•0•Updated Aug 11, 2023Aug 11, 2023

    • ChatGLM-6B

      Public
      ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
      Python
      •
      Apache License 2.0
      •5.2k•2•0•0•Updated Jun 20, 2023Jun 20, 2023

    • pyvlova

      Public
      Yet another Polyhedra Compiler for DeepLearning
      Python
      •
      Apache License 2.0
      •4•19•0•0•Updated Apr 14, 2023Apr 14, 2023