microsoft / BitBLAS
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
☆342Updated this week
Related projects: ⓘ
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆399Updated 2 weeks ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆258Updated 2 months ago
- Code for QuaRot, an end-to-end 4-bit inference of large language models.☆254Updated last month
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆173Updated 3 months ago
- ☆269Updated 5 months ago
- ☆138Updated 2 months ago
- KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆281Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆185Updated last month
- A multi-level tensor algebra superoptimizer☆314Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆560Updated 2 weeks ago
- A collection of memory efficient attention operators implemented in the Triton language.☆204Updated 3 months ago
- Applied AI experiments and examples for PyTorch☆121Updated last month
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆166Updated 11 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆106Updated 6 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆265Updated this week
- FlagGems is an operator library for large language models implemented in Triton Language.☆246Updated this week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆156Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆153Updated 2 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆275Updated last week
- This repository contains the experimental PyTorch native float8 training UX☆210Updated last month
- This repository contains integer operators on GPUs for PyTorch.☆172Updated 11 months ago
- KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆213Updated 3 weeks ago
- The official implementation of the EMNLP 2023 paper LLM-FP4☆156Updated 9 months ago
- ☆102Updated 3 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆81Updated 2 months ago
- Microsoft Automatic Mixed Precision Library☆505Updated 3 weeks ago
- (ICML 2024) BiLLM: Pushing the Limit of Post-Training Quantization for LLMs☆175Updated 3 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆87Updated 3 months ago
- A fast communication-overlapping library for tensor parallelism on GPUs.☆184Updated this week
- GPTQ inference Triton kernel☆273Updated last year