16 results found Sort:

mit-han-lab
temporal-shift-module mit-han-lab
417
2.1k
mit
42
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
tsm low-latency acceleration efficient-model temporal-modeling nvidia-jetson-nano video-understanding
Created 2019-03-27
48 commits to master branch, last one 4 months ago
mit-han-lab
once-for-all mit-han-lab
333
1.9k
mit
53
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
nas automl tinyml edge-ai acceleration efficient-model
Created 2020-01-05
109 commits to master branch, last one about a year ago
mit-han-lab
proxylessnas mit-han-lab
285
1.4k
mit
70
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
automl acceleration on-device-ai hardware-aware specialization efficient-model
Created 2018-12-01
67 commits to master branch, last one 4 months ago
mit-han-lab
amc mit-han-lab
114
430
mit
17
[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices
automl on-device-ai channel-pruning efficient-model model-compression automl-for-compression
Created 2019-06-15
17 commits to master branch, last one 12 months ago
mit-han-lab
haq mit-han-lab
86
370
mit
20
[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision
automl quantization efficient-model mixed-precision
Created 2019-06-14
15 commits to master branch, last one 3 years ago
microsoft
nn-Meter microsoft
60
336
mit
15
A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.
python edge-ai latency pytorch inference onnx-models deep-learning edge-computing efficient-model machine-learning tensorflow-models deep-neural-networks neural-architecture-search
Created 2021-04-26
528 commits to main branch, last one 5 months ago
mit-han-lab
hardware-aware-transformers mit-han-lab
50
330
other
13
[ACL'20] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
transformer hardware-aware specialization efficient-model machine-translation natural-language-processing
Created 2020-05-01
18 commits to master branch, last one 4 months ago
SqueezeAILab
KVQuant SqueezeAILab
26
305
unknown
13
[NeurIPS 2024] 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
12 commits to main branch, last one 4 months ago
amirgholami
ZeroQ amirgholami
56
274
unknown
17
[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework
compression quantization efficient-model efficient-neural-networks quantized-neural-networks
Created 2019-11-20
21 commits to master branch, last one 4 years ago
kssteven418
I-BERT kssteven418
32
229
mit
4
[ICML'21 Oral] I-BERT: Integer-only BERT Quantization
bert transformer quantization efficient-model model-compression efficient-neural-networks natural-language-processing
Created 2020-09-22
1,540 commits to ibert branch, last one 3 years ago
mit-han-lab
amc-models mit-han-lab
27
166
mit
10
[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices
automl on-device-ai efficient-model model-compression
Created 2019-04-08
7 commits to master branch, last one 3 years ago
youngwanLEE
VoV3D youngwanLEE
5
108
other
3
Efficient 3D Backbone Network for Temporal Modeling
vov3d vovnet efficient-model backbone-networks temporal-modeling 3d-cnn-architecture video-understanding
Created 2020-12-28
6 commits to main branch, last one 3 years ago
kssteven418
LTP kssteven418
17
93
apache-2.0
3
[KDD'22] Learned Token Pruning for Transformers
bert pruning transformer efficient-model model-compression efficient-neural-networks natural-language-processing
Created 2021-07-01
7 commits to ltp/main branch, last one about a year ago
szq0214
S2-BNN szq0214
8
63
unknown
2
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)
efficient-model contrastive-loss distillation-loss contrastive-learning binary-neural-networks self-supervised-learning
Created 2021-07-12
10 commits to main branch, last one 3 years ago
xvyaward
owq xvyaward
5
53
unknown
3
Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models".
llm quantization efficient-model large-language-models
Created 2023-06-13
17 commits to main branch, last one 8 months ago
tiangexiang
BiX-NAS tiangexiang
9
38
unknown
3
[MICCAI 2021] BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation
miccai miccai-2021 segmentation efficient-model semantic-segmentation neural-architecture-search
Created 2021-06-26
7 commits to main branch, last one 2 years ago