Fujitsu Research's post-training quantization pipeline for LLMs (QEP, AutoBit, JointQ, rotation) with vLLM plugin (arXiv:2603.28845).
Directory
Search results
Published directory entries matching your search.
Compiler technology to transform a valid Open Neural Network Exchange (ONNX) graph into code that implements the graph with minimum runtime support.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
A library that enables training PyTorch models with differential privacy.
A list of open LLMs available for commercial use.
Grok - An LLM by xAI with and open weights. opensource.
Source code and experiments results for TGS Salt Identification Challenge.
Source code and experiments results for Airbus Ship Detection Challenge.
Source code for Toxic Comment Classification Challenge.
Source code and experiments results for Santander Value Prediction Challenge.
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Open platform for operating large language models (LLMs) in production. Fine-tune, serve, deploy, and monitor any LLMs with ease.
A PyTorch-based framework to train and validate the models producing high-quality embeddings.
A real-time multi-person keypoint detection library for body, face, hands, and foot estimation.
Gitingest - Turn any Git repository into a simple text digest of its codebase so it can be fed into any LLM.
Jan - Run LLMs like Mistral or Llama2 locally and offline on your computer, or connect to remote AI APIs.
An optimization library for Torch. SGD, Adagrad, Conjugate-Gradient, LBFGS, RProp and more.
Google TPU optimizations for transformers models.
Python-based meta-heuristic optimization techniques.
Resource scheduling and cluster management for AI.
A Julia framework for probabilistic graphical models.
Python library for working with Probabilistic Graphical Models.
Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone.