neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
- 2.7k
- Python
- Apache-2.0
- 1 d ago
[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.
Repo ModelTC/LightCompress, read from GitHub 4 h ago. ModelTC has not joined Take My Repo.
ModelTC/LightCompress is a public repo on GitHub by ModelTC. [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models. It declares the Apache-2.0 license on GitHub. It is written mainly in Python, has 755 stars and last changed on 2026-05-14. Nobody has reviewed it on Take My Repo yet, which says nothing about its quality. Read from GitHub on 2026-11-20.
GitHub is limiting requests or did not answer. The facts on this page still come from the last successful read.
Open on GitHubModelTC/LightCompress is a public repo on GitHub by ModelTC. [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.
It declares the Apache-2.0 license on GitHub.
Its maker has not tagged a system, so it is unknown here. Its README says what it needs.
Open "Take it" on its page: Take My Repo writes an install plan for your machine and hands it to your AI agent (Claude Code, Codex or Cursor), which asks you before each step. Take My Repo has not tested it on any machine.
Its last change on GitHub was on 2026-05-14. Take My Repo does not judge from that whether it is maintained.
Nobody has reviewed it on Take My Repo yet, which says nothing about its quality.
A high-throughput and memory-efficient inference and serving engine for LLMs
An open-source, self-hostable PaaS alternative to Vercel, Heroku & Netlify that lets you easily deploy static sites, databases, full-stack applications and 360+ one-click services on your own servers.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.