https://www.anyscale.com/blog/continuous-batching-llm-inference
LLM inference acceleration #Frameworks
LLM inference acceleration #Frameworks
Anyscale
Achieve 23x LLM Inference Throughput & Reduce p50 Latency
In this blog, we discuss continuous batching, a critical systems-level optimization that improves both throughput and latency under load for LLMs.
❤1
Medium
Goodbye databases, it’s time to embrace Vector Databases!
The AI revolution is reshaping industries, promising remarkable innovations while introducing new challenges. In this transformative…
https://codemaker2016.medium.com/goodbye-databases-its-time-to-embrace-vector-databases-0ffa7879980e
#Tips
#Tips
🔥1
https://huggingface.co/collections/osanseviero/model-merging-65097893623330a3a51ead66
Model Merging: papers
#Paper
Model Merging: papers
#Paper
huggingface.co
Model Merging - a osanseviero Collection
Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it!
🔥1
https://github.com/SeldonIO/alibi-detect Algorithms for outlier, adversarial and drift detection
https://github.com/SeldonIO/alibi Algorithms for explaining machine learning models
#Frameworks #library #anomaly #drift
https://github.com/SeldonIO/alibi Algorithms for explaining machine learning models
#Frameworks #library #anomaly #drift
GitHub
GitHub - SeldonIO/alibi-detect: Algorithms for outlier, adversarial and drift detection
Algorithms for outlier, adversarial and drift detection - SeldonIO/alibi-detect
Grokking:
1. Fist paper: https://arxiv.org/abs/2201.02177
2. Transformers: https://arxiv.org/pdf/2405.15071
3. Simple framework: https://arxiv.org/pdf/2405.20233
1. Fist paper: https://arxiv.org/abs/2201.02177
2. Transformers: https://arxiv.org/pdf/2405.15071
3. Simple framework: https://arxiv.org/pdf/2405.20233
arXiv.org
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
In this paper we propose to study generalization of neural networks on small algorithmically generated datasets. In this setting, questions about data efficiency, memorization, generalization, and...
Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and many other libraries.
https://mars-project.readthedocs.io/
#Frameworks
https://mars-project.readthedocs.io/
#Frameworks
Tutorial: Scalable and Distributed ML Workflows with DVC and Ray
Part 1: https://dvc.ai/blog/dvc-ray
Part 2: https://dvc.ai/blog/dvc-ray-part-2
Part 1: https://dvc.ai/blog/dvc-ray
Part 2: https://dvc.ai/blog/dvc-ray-part-2
DVC AI
Tutorial: Scalable and Distributed ML Workflows with DVC and Ray (Part 1)
This tutorial introduces you to integrating DVC (Data Version Control) with Ray, turning them into your go-to toolkit for creating automated, scalable, and distributed ML pipelines.
https://web.stanford.edu/~jurafsky/slp3/
#books Speech and Language Processing (3rd ed. draft)
Dan Jurafsky and James H. Martin
#books Speech and Language Processing (3rd ed. draft)
Dan Jurafsky and James H. Martin
NVidia monitoring #Tools :
1. GPUStat https://github.com/wookayin/gpustat
2. Nvtop https://github.com/Syllo/nvtop
3. NVITOP https://github.com/XuehaiPan/nvitop
1. GPUStat https://github.com/wookayin/gpustat
2. Nvtop https://github.com/Syllo/nvtop
3. NVITOP https://github.com/XuehaiPan/nvitop
SOTA in unsupervised semantic segmentation:
1. STEGO: Unsupervised Semantic Segmentation by Distilling Feature Correspondences - 2022 https://arxiv.org/abs/2203.08414
2. HP: Leveraging Hidden Positives for Unsupervised Semantic Segmentation -2023 https://arxiv.org/abs/2303.15014
3. CAUSE: Causal Unsupervised Semantic Segmentation - 2023 https://arxiv.org/abs/2310.07379
#Paper
1. STEGO: Unsupervised Semantic Segmentation by Distilling Feature Correspondences - 2022 https://arxiv.org/abs/2203.08414
2. HP: Leveraging Hidden Positives for Unsupervised Semantic Segmentation -2023 https://arxiv.org/abs/2303.15014
3. CAUSE: Causal Unsupervised Semantic Segmentation - 2023 https://arxiv.org/abs/2310.07379
#Paper
arXiv.org
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. To solve this task, algorithms must produce...
🔥1
https://arxiv.org/pdf/2408.04840v1
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
#Paper
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
#Paper
https://encord.com/blog/dimentionality-reduction-techniques-machine-learning/
Dimensionality reduction techniques in one place #FYI #Tips
Dimensionality reduction techniques in one place #FYI #Tips
Encord
Top 12 Dimensionality Reduction Techniques for Machine Learning
Dimensionality reduction is a fundamental technique in machine learning (ML) that simplifies datasets by reducing the number of input variables
🔥1
NVidia: Traditional machine learning on GPU: various clustering, UMAP, TSNE, PCA, etc. #FYI #library
https://github.com/rapidsai/cuml
https://docs.rapids.ai/api/cuml/stable/
https://github.com/rapidsai/cuml
https://docs.rapids.ai/api/cuml/stable/
GitHub
GitHub - rapidsai/cuml: cuML - RAPIDS Machine Learning Library
cuML - RAPIDS Machine Learning Library. Contribute to rapidsai/cuml development by creating an account on GitHub.
Numba is an open source JIT compiler that translates a subset of Python and NumPy code into fast machine code.
https://numba.pydata.org/ #Frameworks #library
https://numba.pydata.org/ #Frameworks #library
❤1👏1