spcl / QuaRot
Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.
☆284Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for QuaRot
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆443Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆278Updated 4 months ago
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆158Updated last week
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆241Updated last month
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆305Updated 3 months ago
- This repository contains integer operators on GPUs for PyTorch.☆183Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆208Updated 3 weeks ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆187Updated this week
- The official implementation of the EMNLP 2023 paper LLM-FP4☆167Updated 11 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆222Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆202Updated 2 weeks ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆420Updated this week
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆112Updated 8 months ago
- ☆188Updated 6 months ago
- ☆289Updated 7 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆147Updated 4 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆87Updated last month
- Simple and fast low-bit matmul kernels in CUDA / Triton☆143Updated this week
- Code Repository of Evaluating Quantized Large Language Models☆104Updated 2 months ago
- Applied AI experiments and examples for PyTorch☆166Updated 2 weeks ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆624Updated 2 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆188Updated 3 weeks ago
- EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆224Updated last month
- An easy-to-use package for implementing SmoothQuant for LLMs☆83Updated 6 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆180Updated last year
- DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆373Updated 2 weeks ago
- (ICML 2024) BiLLM: Pushing the Limit of Post-Training Quantization for LLMs☆195Updated 5 months ago
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆254Updated 2 months ago
- An algorithm for static activation quantization of LLMs☆77Updated last week
- Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024☆173Updated 7 months ago