microsoft / BitBLASLinks
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
☆703Updated 2 months ago
Alternatives and similar repositories for BitBLAS
Users that are interested in BitBLAS are comparing it to the libraries listed below
Sorting:
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆770Updated 7 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆266Updated 3 months ago
- Fast low-bit matmul kernels in Triton☆385Updated last week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆433Updated 11 months ago
- A Quirky Assortment of CuTe Kernels☆637Updated 2 weeks ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆253Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆916Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆282Updated last year
- PyTorch emulation library for Microscaling (MX)-compatible data formats☆307Updated 4 months ago
- ☆241Updated last year
- Distributed Compiler based on Triton for Parallel Systems☆1,186Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- A Easy-to-understand TensorOp Matmul Tutorial☆387Updated 2 weeks ago
- Perplexity GPU Kernels☆497Updated last month
- This repository contains integer operators on GPUs for PyTorch.☆220Updated 2 years ago
- Applied AI experiments and examples for PyTorch☆299Updated 2 months ago
- Fastest kernels written from scratch☆377Updated last month
- FlagGems is an operator library for large language models implemented in the Triton Language.☆703Updated this week
- kernels, of the mega variety☆587Updated 3 weeks ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆264Updated this week
- ☆343Updated last year
- flash attention tutorial written in python, triton, cuda, cutlass☆437Updated 5 months ago
- Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators☆478Updated this week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆389Updated last year
- Cataloging released Triton kernels.☆263Updated last month
- ☆242Updated this week
- Shared Middle-Layer for Triton Compilation☆292Updated 2 weeks ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆439Updated this week
- Fast and memory-efficient exact attention☆193Updated last week
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆485Updated last year