11 packages found

torchao

Package for applying ao techniques to GPU models
  1. brrr
  2. cuda
  3. dtypes
  4. float8
  5. inference
  6. llama
  7. mx
  8. offloading
  9. optimizer
  10. pytorch
  11. quantization
  12. sparsity
  13. training
  14. transformer
0.10.0published 4 days agoBSD-3-Clause

neural-compressor

Repository of Intel® Neural Compressor
  1. quantization
  2. auto-tuning
  3. post-training
  4. static
  5. dynamic
  6. quantization-aware
  7. training
  8. awq
  9. fp4
  10. gptq
  11. int4
  12. int8
  13. knowledge-distillation
  14. large-language-models
  15. low-precision
  16. mxformat
  17. post-training-quantization
  18. pruning
  19. quantization-aware-training
  20. smoothquant
  21. sparsegpt
  22. sparsity
112 Contributors
3.3.1published 2 weeks agoApache-2.0

sparseml

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
  1. inference
  2. machine
  3. learning
  4. neural
  5. network
  6. computer
  7. vision
  8. nlp
  9. cv
  10. deep
  11. torch
  12. pytorch
  13. tensorflow
  14. keras
  15. sparsity
  16. pruning
  17. libraries
  18. onnx
  19. quantization
  20. automl
  21. computer-vision-algorithms
  22. deep-learning-algorithms
  23. deep-learning-library
  24. deep-learning-models
  25. image-classification
  26. object-detection
  27. pruning-algorithms
  28. smaller-models
  29. sparsification
  30. sparsification-recipes
  31. transfer-learning
43 Contributors
1.8.0published 10 months agoApache-2.0

neural-compressor-3x-tf

Repository of Intel® Neural Compressor
  1. quantization
  2. auto-tuning
  3. post-training
  4. static
  5. dynamic
  6. quantization-aware
  7. training
  8. awq
  9. fp4
  10. gptq
  11. int4
  12. int8
  13. knowledge-distillation
  14. large-language-models
  15. low-precision
  16. mxformat
  17. post-training-quantization
  18. pruning
  19. quantization-aware-training
  20. smoothquant
  21. sparsegpt
  22. sparsity
3.0published 8 months agoApache-2.0

neural-solution

Repository of Intel® Neural Compressor
  1. quantization
  2. auto-tuning
  3. post-training
  4. static
  5. dynamic
  6. quantization-aware
  7. training
  8. awq
  9. fp4
  10. gptq
  11. int4
  12. int8
  13. knowledge-distillation
  14. large-language-models
  15. low-precision
  16. mxformat
  17. post-training-quantization
  18. pruning
  19. quantization-aware-training
  20. smoothquant
  21. sparsegpt
  22. sparsity
124 Contributors
2.6.1published 9 months agoApache-2.0

deepsparse

An inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application
  1. inference
  2. machine
  3. learning
  4. x86
  5. x86_64
  6. avx2
  7. avx512
  8. neural
  9. network
  10. sparse
  11. engine
  12. cpu
  13. runtime
  14. deepsparse
  15. computer
  16. vision
  17. object
  18. detection
  19. sparsity
  20. computer-vision
  21. cpus
  22. llm-inference
  23. machinelearning
  24. nlp
  25. object-detection
  26. onnx
  27. performance
  28. pretrained-models
  29. pruning
  30. quantization
  31. sparsification
40 Contributors
1.8.0published 9 months agoCDLA-Sharing-1.0

sparsezoo

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
  1. inference
  2. machine
  3. learning
  4. neural
  5. network
  6. deep
  7. model
  8. models
  9. computer
  10. vision
  11. nlp
  12. pretrained
  13. transfer
  14. sparsity
  15. pruning
  16. quantization
  17. sparse
  18. resnet
  19. mobilenet
  20. yolov3
  21. computer-vision
  22. deep-learning-algorithms
  23. deep-learning-models
  24. models-optimized
  25. object-detection-model
  26. pretrained-models
  27. smaller-models
  28. sparse-quantized-models
  29. sparsification-recipe
  30. transfer-learning
  31. yolo
19 Contributors
1.8.1published 9 months agoApache-2.0

nncf

Neural Networks Compression Framework
  1. bert
  2. classification
  3. compression
  4. hawq
  5. mixed-precision-training
  6. mmdetection
  7. nas
  8. nlp
  9. object-detection
  10. pruning
  11. quantization
  12. quantization-aware-training
  13. semantic-segmentation
  14. sparsity
  15. transformers
  16. deep-learning
  17. genai
  18. llm
  19. onnx
  20. openvino
  21. pytorch
  22. tensorflow
73 Contributors
2.16.0published 2 days agoApache-2.0

neural-insights

Repository of Intel® Neural Compressor
  1. quantization
  2. auto-tuning
  3. post-training
  4. static
  5. dynamic
  6. quantization-aware
  7. training
  8. awq
  9. fp4
  10. gptq
  11. int4
  12. int8
  13. knowledge-distillation
  14. large-language-models
  15. low-precision
  16. mxformat
  17. post-training-quantization
  18. pruning
  19. quantization-aware-training
  20. smoothquant
  21. sparsegpt
  22. sparsity
2.6published 10 months agoApache-2.0

paddleslim

A toolkit for generating small model.
  1. PaddleSlim
  2. paddlepaddle
  3. model-optimize
  4. compression
  5. bert
  6. detection
  7. distillation
  8. ernie
  9. nas
  10. pruning
  11. quantization
  12. segmentation
  13. sparsity
  14. tensorrt
  15. transformer
  16. yolov5
  17. yolov6
  18. yolov7
49 Contributors
2.6.0published 1 year agoApache-2.0
Showing 1 to 10 of 11 results