jundaf2 / INT8-Flash-Attention-FMHA-Quantization
☆156Updated last year
Related projects ⓘ
Alternatives and complementary repositories for INT8-Flash-Attention-FMHA-Quantization
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆87Updated 3 months ago
- Applied AI experiments and examples for PyTorch☆159Updated last week
- This repository contains integer operators on GPUs for PyTorch.☆181Updated last year
- ☆88Updated 2 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆196Updated last week
- This repository contains the experimental PyTorch native float8 training UX☆211Updated 3 months ago
- ☆162Updated 3 months ago
- Simple and fast low-bit matmul kernels in CUDA / Triton☆133Updated this week
- ☆121Updated this week
- Fast Hadamard transform in CUDA, with a PyTorch interface☆107Updated 5 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆183Updated last month
- ☆45Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆51Updated last week
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆196Updated 2 months ago
- ☆79Updated 2 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆277Updated 4 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆98Updated last month
- llama INT4 cuda inference with AWQ☆47Updated 4 months ago
- ☆133Updated last year
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆112Updated 8 months ago
- Cataloging released Triton kernels.☆132Updated 2 months ago
- ☆140Updated this week
- ☆55Updated 5 months ago
- Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization☆57Updated this week
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆26Updated 2 months ago
- ☆43Updated this week
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆75Updated 3 weeks ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆146Updated 3 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆278Updated 3 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆79Updated 5 months ago