microsoft / BitBLAS
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
☆420Updated this week
Related projects ⓘ
Alternatives and complementary repositories for BitBLAS
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆443Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆278Updated 4 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆208Updated 3 weeks ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆284Updated 3 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆624Updated 2 months ago
- Applied AI experiments and examples for PyTorch☆166Updated 2 weeks ago
- Simple and fast low-bit matmul kernels in CUDA / Triton☆143Updated this week
- ☆167Updated 4 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆238Updated last week
- A Easy-to-understand TensorOp Matmul Tutorial☆290Updated 2 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆219Updated 5 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆305Updated 3 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆187Updated this week
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆636Updated this week
- This repository contains integer operators on GPUs for PyTorch.☆183Updated last year
- FlagGems is an operator library for large language models implemented in Triton Language.☆342Updated this week
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆112Updated 8 months ago
- A fast communication-overlapping library for tensor parallelism on GPUs.☆224Updated 3 weeks ago
- This repository contains the experimental PyTorch native float8 training UX☆211Updated 3 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆90Updated 4 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆202Updated 5 months ago
- ☆289Updated 7 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆180Updated last year
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆311Updated 2 months ago
- A throughput-oriented high-performance serving framework for LLMs☆636Updated 2 months ago
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆302Updated 2 months ago
- Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024☆173Updated 7 months ago
- Microsoft Automatic Mixed Precision Library☆525Updated last month
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆241Updated last month
- The official implementation of the EMNLP 2023 paper LLM-FP4☆167Updated 11 months ago