Search Results - RepositoryStats

AISystem chenzomi12

1.9k

13.1k

apache-2.0

167

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

ai aisys dlsys mlsys aiinfra

Created 2022-09-22

1,431 commits to main branch, last one 8 days ago

AI-Infra-from-Zero-to-Hero HuaizhengZhang

322

2.8k

mit

127

🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSys...

genai mlsys llmsys ai-infra model-serving model-training large-language-models

Created 2019-01-07

509 commits to master branch, last one 7 months ago

SageAttention thu-ml

86

1.3k

apache-2.0

25

Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

llm cuda mlsys triton attention quantization video-generation efficient-attention inference-acceleration

Created 2024-10-03

86 commits to main branch, last one 9 days ago

nunchaku mit-han-lab

73

1.1k

apache-2.0

20

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

flux iclr lora genai mlsys comfyui iclr2025 quantization diffusion-models

Created 2024-11-06

160 commits to main branch, last one 9 hours ago

AReaL inclusionAI

38

894

apache-2.0

20

Distributed RL System for LLM Reasoning

rl llm mlsys llm-reasoning reinforcement-learning machine-learning-systems

Created 2025-02-24

129 commits to main branch, last one 4 days ago

byteir bytedance

47

418

apache-2.0

12

A model compilation solution for various hardware

llm llvm mlir onnx mlsys pytorch tensorflow

Created 2023-02-06

416 commits to main branch, last one 2 days ago

SpargeAttn thu-ml

24

416

apache-2.0

5

SpargeAttention: A training-free sparse attention that can accelerate any model inference.

llm mlsys ai-infra attention quantization sageattention sparse-attention vision-transformer inference-acceleration

Created 2025-02-25

32 commits to main branch, last one 2 days ago

FedScale SymbioticLab

119

397

apache-2.0

11

FedScale is a scalable and extensible open-source federated learning (FL) platform.

icml osdi mlsys dataset pytorch benchmark deployment tensorflow distributed deep-learning machine-learning federated-learning

Created 2021-04-01

707 commits to master branch, last one about a year ago

zeus ml-energy

33

244

apache-2.0

9

Measure and optimize the energy consumption of your AI applications!

mlsys energy deep-learning

Created 2022-08-13

333 commits to master branch, last one 5 days ago

kernel-ml sbu-fsl

27

242

apache-2.0

17

Machine Learning Framework for Operating Systems - Brings ML to Linux kernel

mlsys auto-tuning linux-kernel kernel-module machine-learning operating-systems

Created 2021-11-10

28 commits to main branch, last one 3 years ago

ABQ-LLM bytedance

21

221

apache-2.0

5

An acceleration library that supports arbitrary bit-width combinatorial quantization operations

cuda mlsys research llm-inference quantized-networks

Created 2024-08-23

57 commits to main branch, last one 6 months ago

Active-Learning-as-a-Service HuaizhengZhang

17

214

apache-2.0

9

A scalable & efficient active learning/data selection system for everyone.

mlops mlsys automl pytorch deep-learning active-learning machine-learning

Created 2022-05-15

110 commits to main branch, last one 9 months ago

Awesome-MLSys-Blogger MLSys-Learner-Resources

3

212

unknown

4

The repository has collected a batch of noteworthy MLSys bloggers (Algorithms/Systems)

llm mlsys llm-training llm-inference machine-learning machine-learning-systems

Created 2025-01-05

10 commits to master branch, last one 3 months ago

ffpa-attn-mma xlite-dev

7

161

gpl-3.0

2

📚FFPA(Split-D): Yet another Faster Flash Prefill Attention with O(1) SRAM complexity large headdim (D > 256), ~2x↑🎉vs SDPA EA.

mla cuda sdpa mlsys deepseek attention flash-mla fused-mla deepseek-r1 deepseek-v3 tensor-cores flash-attention

Created 2024-11-29

247 commits to main branch, last one 12 days ago

BurstGPT HPMLL

9

157

cc-by-4.0

6

A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems

llm mlsys dataset llm-serving

Created 2024-01-30

24 commits to main branch, last one 5 months ago

OSDT xiyanghu

11

103

mit

5

Optimal Sparse Decision Trees

mlsys python neurips python3 algorithm ml-system accelerate data-mining data-science interpretable-ml machine-learning acceleration-model algorithm-optimization

Created 2019-06-05

28 commits to master branch, last one about a year ago

FREE_7773 jacopotagliabue

12

96

mit

5

Materials for my 2021 NYU class on NLP and ML Systems (Master of Engineering).

nlp mlsys metaflow teaching

Created 2021-09-10

42 commits to main branch, last one 2 years ago

FLsystem-paper AmberLJC

6

71

unknown

6

Federated Learning Systems Paper List

mlsys papers systems awesome-list machine-learning federated-learning

Created 2022-04-25

57 commits to main branch, last one about a year ago

sensAI GuanhuaWang

8

64

apache-2.0

8

sensAI: ConvNets Decomposition via Class Parallelism for Fast Inference on Live Data

vgg mlsys sysml resnet cifar10 cifar-10 cifar100 imagenet cifar-100 imagenet1k mobilenet-v2 deep-learning shufflenet-v2 machine-learning cnn-classification distributed-systems deep-neural-networks distributed-deep-learning distributed-machine-learning

Created 2019-03-05

163 commits to master branch, last one 4 years ago