ROCm / flash-attentionLinks
Fast and memory-efficient exact attention
☆179Updated this week
Alternatives and similar repositories for flash-attention
Users that are interested in flash-attention are comparing it to the libraries listed below
Sorting:
- Development repository for the Triton language and compiler☆126Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆260Updated 2 weeks ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆654Updated 3 weeks ago
- GPTQ inference Triton kernel☆303Updated 2 years ago
- Fast low-bit matmul kernels in Triton☆338Updated last week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆365Updated 11 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆318Updated last year
- AI Tensor Engine for ROCm☆243Updated this week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆141Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆86Updated this week
- Applied AI experiments and examples for PyTorch☆289Updated 2 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆224Updated 8 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆730Updated 4 months ago
- The official implementation of the EMNLP 2023 paper LLM-FP4☆211Updated last year
- ☆195Updated 2 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆137Updated 3 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆273Updated last year
- A Quirky Assortment of CuTe Kernels☆374Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆868Updated 11 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆213Updated last year
- Ahead of Time (AOT) Triton Math Library☆74Updated last week
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆206Updated last week
- ☆85Updated 8 months ago
- ☆227Updated last year
- ☆143Updated last month
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆410Updated 8 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 11 months ago
- Reorder-based post-training quantization for large language model☆193Updated 2 years ago
- ☆107Updated 11 months ago