This is your work, valued
tensor_parallel. Automatically split your PyTorch models on multiple GPUs for training & inference
★ 655mipt_lab. MIPT physics lab reports
★ 274ebanko. NLP based telegram bot
★ 59gptq. Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
★ 2BlackSamorez.
★ 2CV22. My CV
★ 1executorch. On-device AI across mobile, embedded and edge for PyTorch
★ 1raytracer22. 2022 iteration of my annual raytracer project.
★ 1looped-moe. code for "Tying the Loop - Tied Expert Layers in Mixture-of-Experts Language Models"
★ 7slides. Vue
★ 1OneCompression. Python package for LLM compression
★ 397Quartet-II. Quartet II Official Code
★ 75FP-Quant. Python
★ 114QuickRecap. An iOS app that integrates a Large Language Model (LLM) to process audio recordings for transcription and summarization.
★ 17qutlass. QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
★ 187Quartet. Jupyter Notebook
★ 126circle-guard-bench. First-of-its-kind AI benchmark for evaluating the protection capabilities of large language model (LLM) guard systems (guardrails and safeguards)
★ 70cline. Autonomous coding agent as an SDK, IDE extension, or CLI assistant.
★ 65kMathador-LM. Code for the EMNLP 2024 paper "Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on LLMs".
★ 8qtip. Python
★ 180QQQ. QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
★ 156CPP_from_1998_to_2020. Technical Note: From C++98 to C++2x
★ 147QUICK. QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
★ 123marlin. FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
★ 1.1kQuIP-for-all. QuIP quantization
★ 66AQLM. Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852
★ 1.3kadhd_helper. Go
★ 5FriendsDontLetFriends. Friends don't let friends make certain types of data visualization - What are they and why are they bad.
★ 7.1kquip-sharp. Python
★ 600gptq. Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
★ 2.3kqmoe. Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".
★ 278meditron. Meditron is a suite of open-source medical Large Language Models (LLMs).
★ 2.2kLookaheadDecoding. [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
★ 1.3kPFL-DocVQA-Competition. Python
★ 21QUIK. Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024
★ 185optim. 💎A site, that contains systematic optimization methods and theory review
★ 137Megatron-LLM. distributed trainer for LLMs
★ 589candle. Minimalist ML framework for Rust
★ 21kEDEN-Distributed-Mean-Estimation. This repository is the official implementation of 'EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning' (ICML 2022).
★ 18spellah. A nasty project for the 2014's Microsoft Research Summer School.
★ 1llama2.c. Inference Llama 2 in one file of pure C
★ 20kCocktailSGD. Python
★ 27GPU-Puzzles. Solve puzzles. Learn CUDA.
★ 12kSpQR. Python
★ 554plusplus. Enables increment operators in Python using a bytecode hack
★ 94g-helper. Lightweight Armoury Crate alternative for Asus laptops with nearly the same functionality. Works with ROG Zephyrus, Flow, TUF, Strix, Scar, ProArt, Vivobook, Zenbook, Expertbook, ROG Ally, and many more.
★ 14kwhat-happens-when. An attempt to answer the age old interview question "What happens when you type google.com into your browser and press enter?"
★ 43kSoulsGym. Gymnasium extension for DarkSouls III, Elden Ring, and other Souls games
★ 154lightning-Hivemind. Lightning Training strategy for HiveMind
★ 18peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
★ 21kDialog. A PyTorch Implementation of japanese chatbot using BERT and Transformer's decoder
★ 72wasm4-raycaster. A demo raycaster for the WASM-4 engine.
★ 92shad-go. Golang programming course
★ 472FBGEMM. FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
★ 1.6kbitsandbytes. Accessible large language models via k-bit quantization for PyTorch.
★ 8.3kPractical_RL. A course in reinforcement learning in the wild
★ 6.5kUnnaturalScrollWheels. Invert scroll direction for physical scroll wheels while maintaining "Natural" scrolling for trackpads on MacOS
★ 4.1kmatchering. 🎚️ Open Source Audio Matching and Mastering
★ 2.6kspeedscope. 🔬 A fast, interactive web-based viewer for performance profiles.
★ 6.7kefficient-dl-systems. Efficient Deep Learning Systems course materials (HSE, YSDA)
★ 1kvk-clones. Python
★ 13qiskit. Qiskit is an open-source SDK for working with quantum computers at the level of extended quantum circuits, operators, and primitives.
★ 7.6k4chan-x. Adds various features to anonymous imageboards.
★ 1.1k