mirage-project / mirage

Related projects: ⓘ

• microsoft / BitBLAS
  BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
  ☆342Updated this week
• pytorch-labs / float8_experimental
  This repository contains the experimental PyTorch native float8 training UX
  ☆210Updated last month
• Deep-Learning-Profiling-Tools / triton-viz
  ☆124Updated last week
• BobMcDear / attorch
  A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
  ☆452Updated last week
• pytorch-labs / applied-ai
  Applied AI experiments and examples for PyTorch
  ☆121Updated last month
• HanGuo97 / flute
  Fast Matrix Multiplications for Lookup Table-Quantized LLMs
  ☆156Updated this week
• cuda-mode / triton-index
  Cataloging released Triton kernels.
  ☆108Updated 3 weeks ago
• spcl / QuaRot
  Code for QuaRot, an end-to-end 4-bit inference of large language models.
  ☆254Updated last month
• tspeterkim / flash-attention-minimal
  Flash Attention in ~100 lines of CUDA (forward pass only)
  ☆558Updated 5 months ago
• mit-han-lab / qserve
  QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
  ☆399Updated 2 weeks ago
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆258Updated 2 months ago
• ColfaxResearch / cutlass-kernels
  ☆138Updated 2 months ago
• zinccat / Awesome-Triton-Kernels
  Collection of kernels written in Triton language
  ☆48Updated 2 weeks ago
• google / aqt
  ☆247Updated this week
• foundation-model-stack / foundation-model-stack
  🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.
  ☆144Updated this week
• IST-DASLab / marlin
  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
  ☆560Updated 2 weeks ago
• efeslab / fiddler
  Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆163Updated 3 months ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆173Updated 3 months ago
• efeslab / Nanoflow
  A throughput-oriented high-performance serving framework for LLMs
  ☆470Updated this week
• Infini-AI-Lab / Sequoia
  scalable and robust tree-based speculative decoding algorithm
  ☆298Updated last month
• lucidrains / ring-attention-pytorch
  Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch
  ☆451Updated last month
• IST-DASLab / QUIK
  Repository for the QUIK project, enabling the use of 4bit kernels for generative inference
  ☆167Updated 5 months ago
• cuda-mode / ring-attention
  ring-attention experiments
  ☆89Updated 5 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆81Updated 2 months ago
• shawntan / scattermoe
  Triton-based implementation of Sparse Mixture of Experts.
  ☆166Updated 3 weeks ago
• forhaoliu / ringattention
  Transformers with Arbitrarily Large Context
  ☆613Updated last month
• Cornell-RelaxML / QuIP
  Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"
  ☆339Updated 6 months ago
• SqueezeAILab / KVQuant
  KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  ☆281Updated last month
• zhuzilin / ring-flash-attention
  Ring attention implementation with flash attention
  ☆529Updated this week
• siboehm / SGEMM_CUDA
  Fast CUDA matrix multiplication from scratch
  ☆420Updated 8 months ago