Yassine (yassouali)

yassouali

Geek Repo

Company:CentraleSupelec

Location:France

Home Page:yassouali.github.io

Twitter:@yass_ouali

Github PK Tool:Github PK Tool

Yassine's starred repositories

nvtop

GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

Language:CLicense:NOASSERTIONStargazers:7616Issues:0Issues:0

shap

A game theoretic approach to explain the output of any machine learning model.

Language:Jupyter NotebookLicense:MITStargazers:21937Issues:0Issues:0

functionary

Chat language model that can use tools and interpret the results

Language:PythonLicense:MITStargazers:1166Issues:0Issues:0

awesome-ml-on-device

Machine Learning On-Device Universe

License:MITStargazers:4Issues:0Issues:0

trackerjacker

Like nmap for mapping wifi networks you're not connected to, plus device tracking

Language:PythonLicense:MITStargazers:2594Issues:0Issues:0

Perplexica

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

Language:TypeScriptLicense:MITStargazers:7944Issues:0Issues:0

Tensor-Puzzles

Solve puzzles. Improve your pytorch.

Language:Jupyter NotebookLicense:MITStargazers:2865Issues:0Issues:0

Bend

A massively parallel, high-level programming language

Language:RustLicense:Apache-2.0Stargazers:16190Issues:0Issues:0

marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Language:PythonLicense:Apache-2.0Stargazers:402Issues:0Issues:0

Glider

Open-source E-ink monitor. Mirror of https://gitlab.com/zephray/glider

Language:CLicense:NOASSERTIONStargazers:1485Issues:0Issues:0

ThunderKittens

Tile primitives for speedy kernels

Language:CudaLicense:MITStargazers:1281Issues:0Issues:0

datatype99

Algebraic data types for C99

Language:CLicense:MITStargazers:1329Issues:0Issues:0

cohere-toolkit

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

Language:TypeScriptLicense:MITStargazers:2308Issues:0Issues:0

tiny-gpu

A minimal GPU design in Verilog to learn how GPUs work from the ground up

Language:SystemVerilogStargazers:6436Issues:0Issues:0

faer-rs

Linear algebra foundation for the Rust programming language

Language:RustLicense:MITStargazers:1713Issues:0Issues:0

axolotl

Go ahead and axolotl questions

Language:PythonLicense:Apache-2.0Stargazers:6522Issues:0Issues:0

ao

Native PyTorch library for quantization and sparsity

Language:PythonLicense:BSD-3-ClauseStargazers:305Issues:0Issues:0

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

Language:Jupyter NotebookStargazers:10095Issues:0Issues:0

torchtune

A Native-PyTorch Library for LLM Fine-tuning

Language:PythonLicense:BSD-3-ClauseStargazers:3396Issues:0Issues:0

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

Language:PythonLicense:MITStargazers:11643Issues:0Issues:0

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Language:PythonLicense:MITStargazers:1339Issues:0Issues:0

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

Language:PythonLicense:MITStargazers:3110Issues:0Issues:0

lm-evaluation-harness

A framework for few-shot evaluation of language models.

Language:PythonLicense:MITStargazers:5507Issues:0Issues:0

VoiceCraft

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:7000Issues:0Issues:0

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

Language:PythonLicense:Apache-2.0Stargazers:2622Issues:0Issues:0

llm.c

LLM training in simple, raw C/CUDA

Language:CudaLicense:MITStargazers:20657Issues:0Issues:0

ipex-llm

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, Axolotl, etc.

Language:PythonLicense:Apache-2.0Stargazers:6144Issues:0Issues:0

supervision

We write your reusable computer vision tools. 💜

Language:PythonLicense:MITStargazers:14993Issues:0Issues:0

cutlass

CUDA Templates for Linear Algebra Subroutines

Language:C++License:NOASSERTIONStargazers:4739Issues:0Issues:0

Triton-Puzzles

Puzzles for learning Triton

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:750Issues:0Issues:0