22 results found Sort:

huawei-noah
Efficient-AI-Backbones huawei-noah
690
3.9k
unknown
51
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
pytorch ghostnet imagenet tensorflow transformer model-compression pretrained-models vision-transformer efficient-inference convolutional-neural-networks
Created 2019-11-16
148 commits to master branch, last one about a month ago
SqueezeAILab
LLMCompiler SqueezeAILab
80
1.2k
mit
18
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
llm nlp llms llama llama2 llm-agent llm-agents transformer llm-framework function-calling efficient-inference large-language-models parallel-function-call natural-language-processing
Created 2023-12-06
50 commits to main branch, last one about a month ago
snap-research
EfficientFormer snap-research
91
961
other
36
EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]
pytorch imagenet detection transformer transformers deep-learning mobile-devices efficient-inference semantic-segmentation efficient-neural-networks
Created 2022-06-02
23 commits to main branch, last one 11 months ago
huawei-noah
AdderNet huawei-noah
186
948
bsd-3-clause
25
Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"
pytorch cvpr2020 imagenet efficient-inference convolutional-neural-networks
Created 2020-02-25
31 commits to master branch, last one 2 years ago
horseee
DeepCache horseee
32
644
apache-2.0
17
[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
training-free diffusion-models stable-diffusion model-compression efficient-inference
Created 2023-12-01
124 commits to master branch, last one 8 days ago
SqueezeAILab
SqueezeLLM SqueezeAILab
37
588
mit
17
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
llm llama localllm transformer quantization small-models text-generation model-compression efficient-inference large-language-models post-training-quantization natural-language-processing
Created 2023-06-12
50 commits to main branch, last one 2 months ago
VITA-Group
LightGaussian VITA-Group
34
483
other
33
"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
3d-reconstruction gaussian-splatting efficient-inference
Created 2023-11-26
68 commits to main branch, last one 3 months ago
Zhen-Dong
Awesome-Quantization-Papers Zhen-Dong
37
333
mit
9
List of papers related to neural network quantization in recent AI conferences and journals.
papers awesome-list quantization edge-computing neural-networks diffusion-models model-compression efficient-inference large-language-models
Created 2022-01-01
31 commits to main branch, last one 16 days ago
The-Learning-And-Vision-Atelier-LAVA
SMSR The-Learning-And-Vision-Atelier-LAVA
29
235
unknown
7
[CVPR 2021] Exploring Sparsity in Image Super-Resolution for Efficient Inference
sparsity super-resolution efficient-inference
Created 2020-07-26
38 commits to master branch, last one 2 years ago
changlin31
DS-Net changlin31
19
225
unknown
9
(CVPR 2021, Oral) Dynamic Slimmable Network
pruning dynamic-pruning network-pruning dynamic-networks model-compression efficient-inference
Created 2021-03-23
12 commits to main branch, last one 2 years ago
SqueezeAILab
KVQuant SqueezeAILab
17
218
unknown
14
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
llm llama mistral localllm localllama compression transformer quantization small-models efficient-model text-generation model-compression efficient-inference large-language-models natural-language-processing
Created 2024-01-31
10 commits to main branch, last one about a month ago
xindongzhang
ELAN xindongzhang
17
192
apache-2.0
8
[ECCV2022] Efficient Long-Range Attention Network for Image Super-resolution
transformer super-resolution efficient-inference
Created 2022-03-12
8 commits to main branch, last one about a year ago
cure-lab
DeciWatch cure-lab
16
171
apache-2.0
9
[ECCV 2022] Official implementation of the paper "DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation"
eccv pytorch eccv2022 efficiency 2d-human-pose deep-learning pose-estimation 3d-body-recovery 3d-pose-estimation body-reconstruction efficient-inference human-pose-estimation efficient-neural-networks
Created 2022-04-25
47 commits to main branch, last one about a year ago
lucidrains
speculative-decoding lucidrains
14
166
mit
8
Explorations into some recent techniques surrounding speculative decoding
transformers deep-learning efficient-inference artificial-intelligence
Created 2023-08-27
71 commits to main branch, last one 8 months ago
Picovoice
picollm Picovoice
2
104
apache-2.0
7
On-device LLM Inference Powered by X-Bit Quantization
llm llms gemma llama llama2 llama3 mistral mixtral compression self-hosted quantization generative-ai llm-infernece language-model language-models model-compression efficient-inference large-language-model natural-language-processing
Created 2024-04-09
17 commits to main branch, last one a day ago
RAIVNLab
STR RAIVNLab
11
84
apache-2.0
7
Soft Threshold Weight Reparameterization for Learnable Sparsity
cnn str icml icml2020 imagenet sparsity icml-2020 soft-thresholding learnable-sparsity resource-efficient efficient-inference edge-machine-learning sparsity-optimization soft-threshold-reparameterization
Created 2020-04-11
53 commits to master branch, last one 2 years ago
kssteven418
BigLittleDecoder kssteven418
9
82
apache-2.0
6
[NeurIPS'23] Speculative Decoding with Big Little Decoder
llm decoding fast-inference efficient-inference speculative-decoding speculative-execution
Created 2023-02-10
11,217 commits to main branch, last one 4 months ago
snap-research
graphless-neural-networks snap-research
20
80
mit
8
[ICLR 2022] Code for Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation (GLNN)
gnn pytorch scalability distillation deep-learning graph-algorithm efficient-inference graph-neural-networks knowledge-distillation
Created 2021-10-27
24 commits to main branch, last one about a year ago
FranxYao
Partially-Observed-TreeCRFs FranxYao
7
52
unknown
4
Implementation of AAAI 21 paper: Nested Named Entity Recognition with Partially Observed TreeCRFs
crf tree-crf sum-product tree-structure efficient-inference sum-product-algorithm named-entity-recognition nested-named-entity-recognition
Created 2020-12-10
10 commits to main branch, last one 3 years ago
IBM
AdaMML IBM
9
49
apache-2.0
6
Official implementation of AdaMML. https://arxiv.org/abs/2105.05165.
deep-learning computer-vision efficient-inference multimodal-learning
Created 2021-10-07
16 commits to main branch, last one 2 years ago
tchittesh
lzu tchittesh
5
46
mit
2
Code for Learning to Zoom and Unzoom (CVPR 2023)
3d-detection spatial-attention autonomous-driving efficient-inference
Created 2023-03-16
7 commits to main branch, last one about a year ago
raymin0223
fast_robust_early_exit raymin0223
8
44
unknown
2
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)
nlp llms early-exiting efficient-inference autoregressive-models
Created 2023-06-26
18 commits to main branch, last one a day ago