mfuntowicz/lmir
Language Model Intermediate Representation
@huggingface | Low-level stuff
Repositories
mfuntowicz/hmll
HMLL - High-Performance Model Loading Library for Efficient AI Model I/O
mfuntowicz/kernels
mfuntowicz/llama.cpp
LLM inference in C/C++
mfuntowicz/ionic
mfuntowicz/hmll-devel
Experiment tracking for hmll repository - exploring not so clear paths and ideas that leads certainly nowhere
mfuntowicz/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
mfuntowicz/Pilot
mfuntowicz/installama.sh
The fastest way to install llama.cpp
mfuntowicz/kitok
Lightning Fast LLM Tokenizer
mfuntowicz/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
mfuntowicz/safetensors
Pure C based implementation of safetensors deserialization
mfuntowicz/AI-Trader
"AI-Trader: Can AI Beat the Market?" Live Trading: https://hkuds.github.io/AI-Trader/
mfuntowicz/lighteval
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
mfuntowicz/piweather
Turn your Raspberry Pi into a powerful weather station
mfuntowicz/flat6
mfuntowicz/TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
mfuntowicz/RNet
PyTorch RNet implementation with Distributed and Mixed-Precision training support.
mfuntowicz/2DCuttingProblem
2D Cutting Problem solution generator using metaheuristic methods and linear programming
mfuntowicz/llama2.rs
mfuntowicz/rust-bindgen
Automatically generates Rust FFI bindings to C (and some C++) libraries.
mfuntowicz/deep-learning-containers
AWS Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet.
mfuntowicz/apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
mfuntowicz/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
mfuntowicz/server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
mfuntowicz/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
mfuntowicz/onnxruntime_backend
The Triton backend for the ONNX Runtime.
mfuntowicz/onnx
Open standard for machine learning interoperability
mfuntowicz/flax
Flax is a neural network library for JAX that is designed for flexibility.
mfuntowicz/fastBPE
Fast BPE