jundaf2 / INT8-Flash-Attention-FMHA-QuantizationLinks
☆159Updated 2 years ago
Alternatives and similar repositories for INT8-Flash-Attention-FMHA-Quantization
Users that are interested in INT8-Flash-Attention-FMHA-Quantization are comparing it to the libraries listed below
Sorting:
- This repository contains the experimental PyTorch native float8 training UX☆224Updated last year
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆115Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆123Updated 4 months ago
- This repository contains integer operators on GPUs for PyTorch.☆218Updated 2 years ago
- ☆112Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 2 months ago
- Applied AI experiments and examples for PyTorch☆296Updated last month
- Benchmark code for the "Online normalizer calculation for softmax" paper☆100Updated 7 years ago
- ☆82Updated 8 months ago
- ☆156Updated 2 years ago
- ☆161Updated 2 years ago
- llama INT4 cuda inference with AWQ☆55Updated 8 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆230Updated this week
- pytorch-profiler☆51Updated 2 years ago
- A collection of memory efficient attention operators implemented in the Triton language.☆279Updated last year
- Fast Hadamard transform in CUDA, with a PyTorch interface☆239Updated 3 weeks ago
- A Python library transfers PyTorch tensors between CPU and NVMe☆121Updated 10 months ago
- extensible collectives library in triton☆88Updated 6 months ago
- Reorder-based post-training quantization for large language model☆195Updated 2 years ago
- Fast low-bit matmul kernels in Triton☆373Updated last week
- An easy-to-use package for implementing SmoothQuant for LLMs☆106Updated 5 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆99Updated 3 weeks ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated last year
- ☆238Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆82Updated last year
- The official implementation of the EMNLP 2023 paper LLM-FP4☆215Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆213Updated last week
- PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.☆111Updated 10 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆84Updated 2 weeks ago