Highlights
- Pro
Stars
TradingAgents: Multi-Agents LLM Financial Trading Framework
Security oriented software fuzzer. Supports evolutionary, feedback-driven fuzzing based on code coverage (SW and HW based)
Source code for the architectural simulator used for modeling the PUD system proposed in our HPCA 2024 paper `MIMDRAM: An End-to-End Processing-Using-DRAM System for High-Throughput, Energy-Efficie…
The portal to the new, open Internet. ([I:b])
Running large language models on a single GPU for throughput-oriented scenarios.
A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (p…
Implementation of Nougat Neural Optical Understanding for Academic Documents
🦜🔗 The platform for reliable agents.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
Measure and optimize the energy consumption of your AI applications!
⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
SuperSonic, a new open-source framework to allow compiler developers to integrate RL into compilers easily, regardless of their RL expertise.
NeuroVectorizer is a framework that uses deep reinforcement learning (RL) to predict optimal vectorization compiler pragmas for for loops in C and C++ codes.