☆87Jan 23, 2025Updated last year
Alternatives and similar repositories for INT-FlashAttention
Users that are interested in INT-FlashAttention are comparing it to the libraries listed below
Sorting:
- ☆97Feb 26, 2026Updated last week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆21Feb 9, 2026Updated last month
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆172Nov 26, 2025Updated 3 months ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆73Sep 8, 2024Updated last year
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆374Feb 14, 2025Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆817Mar 6, 2025Updated last year
- Fast low-bit matmul kernels in Triton☆436Feb 1, 2026Updated last month
- ☆52May 19, 2025Updated 9 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆23Mar 15, 2024Updated last year
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆388Apr 13, 2025Updated 10 months ago
- Triton kernels for Flux☆22Jul 7, 2025Updated 8 months ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆210Nov 25, 2025Updated 3 months ago
- ☆118May 19, 2025Updated 9 months ago
- ☆65Apr 26, 2025Updated 10 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆154Aug 21, 2025Updated 6 months ago
- Persistent dense gemm for Hopper in `CuTeDSL`☆15Aug 9, 2025Updated 6 months ago
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆83Jul 28, 2025Updated 7 months ago
- ☆20Sep 28, 2024Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆336Jul 2, 2024Updated last year
- [WIP] Better (FP8) attention for Hopper☆32Feb 24, 2025Updated last year
- ☆160Sep 15, 2023Updated 2 years ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆93Sep 4, 2024Updated last year
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆71Jul 8, 2025Updated 8 months ago
- ACL 2023☆39Jun 6, 2023Updated 2 years ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆107Jun 28, 2025Updated 8 months ago
- A quantization algorithm for LLM☆148Jun 21, 2024Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆358Nov 20, 2025Updated 3 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,035Sep 4, 2024Updated last year
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆81Dec 18, 2025Updated 2 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆234Sep 24, 2023Updated 2 years ago
- ☆15Sep 22, 2024Updated last year
- Benchmark tests supporting the TiledCUDA library.☆18Nov 19, 2024Updated last year
- ☆62Feb 15, 2026Updated 3 weeks ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆285Oct 19, 2025Updated 4 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆288Jun 5, 2024Updated last year
- [ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Mod…☆31Mar 12, 2024Updated last year
- An experimental communicating attention kernel based on DeepEP.☆35Jul 29, 2025Updated 7 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆405Aug 13, 2024Updated last year