IntelLabs / FP8-Emulation-ToolkitLinks
PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.
☆110Updated 6 months ago
Alternatives and similar repositories for FP8-Emulation-Toolkit
Users that are interested in FP8-Emulation-Toolkit are comparing it to the libraries listed below
Sorting:
- ☆149Updated 2 years ago
- ☆146Updated 10 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆109Updated 10 months ago
- This repository contains integer operators on GPUs for PyTorch.☆205Updated last year
- ☆58Updated last year
- ☆96Updated last year
- PyTorch emulation library for Microscaling (MX)-compatible data formats☆241Updated this week
- play gemm with tvm☆91Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆92Updated last week
- llama INT4 cuda inference with AWQ☆54Updated 4 months ago
- SparseTIR: Sparse Tensor Compiler for Deep Learning☆138Updated 2 years ago
- A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores☆51Updated last year
- Fast Hadamard transform in CUDA, with a PyTorch interface☆192Updated last year
- Benchmark code for the "Online normalizer calculation for softmax" paper☆94Updated 6 years ago
- ☆156Updated last year
- ☆73Updated 4 months ago
- ☆86Updated 5 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆251Updated 7 months ago
- ☆208Updated 10 months ago
- An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.☆50Updated 10 months ago
- Artifacts of EVT ASPLOS'24☆25Updated last year
- DeeperGEMM: crazy optimized version☆69Updated 3 weeks ago
- ☆109Updated 3 weeks ago
- ☆96Updated 8 months ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆62Updated 8 months ago
- ☆49Updated 10 months ago
- Automatic Mapping Generation, Verification, and Exploration for ISA-based Spatial Accelerators☆110Updated 2 years ago
- DietCode Code Release☆64Updated 2 years ago
- PyTorch bindings for CUTLASS grouped GEMM.☆93Updated last week
- pytorch-profiler☆51Updated 2 years ago