☆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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆390Feb 14, 2025Updated last year
- ☆107Feb 26, 2026Updated 2 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆155Aug 21, 2025Updated 8 months ago
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆89Jul 28, 2025Updated 9 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆22Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Fast low-bit matmul kernels in Triton☆446Apr 27, 2026Updated last week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆391Apr 13, 2025Updated last year
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆23Mar 15, 2024Updated 2 years ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆171Nov 26, 2025Updated 5 months ago
- ☆52May 19, 2025Updated 11 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆835Mar 6, 2025Updated last year
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆74Sep 8, 2024Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆96Sep 4, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆338Jul 2, 2024Updated last year
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆214Nov 25, 2025Updated 5 months ago
- Triton kernels for Flux☆23Jul 7, 2025Updated 10 months ago
- ☆38Aug 7, 2025Updated 9 months ago
- ☆162Sep 15, 2023Updated 2 years ago
- ☆119May 19, 2025Updated 11 months ago
- ☆20Sep 28, 2024Updated last year
- Official PyTorch implementation of "GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance" (ICML 2025)☆51Apr 13, 2026Updated 3 weeks ago
- ☆66Apr 26, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Get Moving with Pynq on Alveo U50☆13Jul 13, 2020Updated 5 years ago
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated 9 months ago
- ACL 2023☆39Jun 6, 2023Updated 2 years ago
- A quantization algorithm for LLM☆149Jun 21, 2024Updated last year
- [COLM 2025] DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation; 知乎：https://zhuanlan.zhihu.c…☆30Mar 5, 2025Updated last year
- [WIP] Better (FP8) attention for Hopper☆33Feb 24, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,065Sep 4, 2024Updated last year
- Fast Hadamard transform in CUDA, with a PyTorch interface☆311Mar 10, 2026Updated last month
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆73Jul 8, 2025Updated 10 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- ☆63Jul 21, 2024Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆390Nov 20, 2025Updated 5 months ago
- FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA.☆277Updated this week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆421Aug 13, 2024Updated last year
- A safetensors extension to efficiently store sparse quantized tensors on disk☆275May 1, 2026Updated last week
- A Easy-to-understand TensorOp Matmul Tutorial☆428Mar 5, 2026Updated 2 months ago