INT-FlashAttention2024 / INT-FlashAttentionLinks
☆82Updated 9 months ago
Alternatives and similar repositories for INT-FlashAttention
Users that are interested in INT-FlashAttention are comparing it to the libraries listed below
Sorting:
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆60Updated last week
- PyTorch bindings for CUTLASS grouped GEMM.☆125Updated 4 months ago
- ☆58Updated last year
- ☆65Updated 6 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 7 months ago
- Quantized Attention on GPU☆44Updated 11 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆120Updated this week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆117Updated last year
- ☆120Updated 2 months ago
- LLM Inference with Microscaling Format☆31Updated 11 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆253Updated last week
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆160Updated 5 months ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆179Updated 2 weeks ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆144Updated 2 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆107Updated 6 months ago
- DeeperGEMM: crazy optimized version☆72Updated 5 months ago
- ☆102Updated 5 months ago
- llama INT4 cuda inference with AWQ☆55Updated 9 months ago
- Implement Flash Attention using Cute.☆96Updated 10 months ago
- ☆79Updated last year
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆68Updated 3 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆169Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- ☆153Updated last year
- 16-fold memory access reduction with nearly no loss☆105Updated 7 months ago
- ☆100Updated last year
- ☆36Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆84Updated last year
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆266Updated 3 months ago