SqueezeBits / QUICK
QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
☆116Updated last year
Alternatives and similar repositories for QUICK:
Users that are interested in QUICK are comparing it to the libraries listed below
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆298Updated 8 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 8 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆67Updated 6 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆237Updated 4 months ago
- This repository contains integer operators on GPUs for PyTorch.☆193Updated last year
- ☆62Updated last month
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆97Updated 2 months ago
- Fast low-bit matmul kernels in Triton☆254Updated this week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆231Updated 2 weeks ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆107Updated 3 weeks ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆356Updated 3 months ago
- ☆187Updated 8 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆151Updated 9 months ago
- Applied AI experiments and examples for PyTorch☆243Updated this week
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆278Updated last month
- ☆84Updated 6 months ago
- ☆115Updated 3 weeks ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆335Updated 6 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆103Updated this week
- The official implementation of the EMNLP 2023 paper LLM-FP4☆187Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆109Updated 3 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆201Updated last year
- This repository contains the experimental PyTorch native float8 training UX☆222Updated 7 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆118Updated last month
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆108Updated last month
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆253Updated 3 months ago
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆228Updated 3 weeks ago
- ☆52Updated 11 months ago
- llama INT4 cuda inference with AWQ☆53Updated last month
- ☆229Updated 10 months ago