ModelTC / LightCompressLinks
A powerful toolkit for compressing large models including LLM, VLM, and video generation models.
☆576Updated last month
Alternatives and similar repositories for LightCompress
Users that are interested in LightCompress are comparing it to the libraries listed below
Sorting:
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆559Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆760Updated 7 months ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆170Updated last week
- FlagGems is an operator library for large language models implemented in the Triton Language.☆690Updated this week
- FlagScale is a large model toolkit based on open-sourced projects.☆358Updated last week
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆315Updated 7 months ago
- Awesome list for LLM quantization☆312Updated last week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆429Updated 10 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆141Updated last month
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆412Updated this week
- This repository contains integer operators on GPUs for PyTorch.☆218Updated 2 years ago
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆333Updated 7 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆902Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆571Updated 2 weeks ago
- ☆140Updated last year
- Fast inference from large lauguage models via speculative decoding☆829Updated last year
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆476Updated last year
- ☆129Updated 9 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆425Updated 4 months ago
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆108Updated 2 months ago
- ☆147Updated 7 months ago
- export llama to onnx☆136Updated 9 months ago
- A quantization algorithm for LLM☆143Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆279Updated last year
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆265Updated 2 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆527Updated 2 weeks ago
- Disaggregated serving system for Large Language Models (LLMs).☆697Updated 6 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆314Updated 5 months ago
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆806Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year