这是一个基于C++实现的从零开始的大模型推理框架
☆10Nov 18, 2024Updated last year
Alternatives and similar repositories for LLM_infra_from_scratch
Users that are interested in LLM_infra_from_scratch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 这是一个从零学习CUDA课程☆13Nov 3, 2024Updated 2 years ago
- 2025.3.18再次更新！新增查询余额功能！ChatGPT-website的改进版本（后端请求），几乎支持所有OpenAI模型，新增前端设置参数（temperature和tokens），gpt4访问密码，记忆和读取参数（cookies），apikey支持批量填写（前端以及…☆14Jan 4, 2026Updated 10 months ago
- 记录笔者对于Stanford CS231n这门课程的三个课程作业及课程笔记☆10Mar 1, 2026Updated 8 months ago
- A unified framework for feed-forward neural networks☆16Nov 28, 2025Updated 11 months ago
- Ollama Function Calling with Search API☆11Apr 28, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Love 2d based Tetris game☆13May 21, 2013Updated 13 years ago
- SeekMate is an unofficial NodeSeek client for Android☆15Oct 30, 2026Updated last week
- simplest online-softmax notebook for explain Flash Attention☆18Jan 27, 2026Updated 9 months ago
- Scalable toolkit for efficient model reinforcement☆14Oct 22, 2026Updated 2 weeks ago
- 3D Gaussian Splat Easily Attacked to Cause Harm☆13Aug 5, 2025Updated last year
- Demonstration of a factory pattern where the types automatically register themselves☆13Mar 13, 2019Updated 7 years ago
- rule matcher (context free grammar)☆10Dec 27, 2019Updated 6 years ago
- 本项目旨在将个人微信/QQ 聊天记录转化为一个风格高度拟人、具备长期记忆的本地 AI 对话伴侣。通过 QLoRA 微调技术克隆说话语气，结合向量数据库实现往事回忆，并支持在回复中自动触发对应的表情包，营造与真人好友聊天的沉浸体验。☆19May 8, 2026Updated 6 months ago
- a within-document event coreference resolution system, trained and evaluated on the KBP corpus.☆10May 15, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Let's build a completely self-hosting Lua compiler from scratch (that means regex, lexer, parser, bytecode, the whole nine yards!)☆12Dec 2, 2015Updated 10 years ago
- ☆10Apr 20, 2025Updated last year
- VLSI placement and routing tool☆16Dec 20, 2025Updated 10 months ago
- using taichi to create sph simulation☆49Jul 22, 2022Updated 4 years ago
- zero-overhead SSH protection at XDP speed. Guard your SSH like tyr guard the gates of asgard!☆11May 2, 2025Updated last year
- python interface for mate tools☆17Jan 23, 2018Updated 8 years ago
- ☆14Mar 5, 2023Updated 3 years ago
- An example of getting started with Android ebpf☆12Aug 23, 2023Updated 3 years ago
- My solutions to the assignments of dlsys course (CSE599G1: Deep Learning System Spring 2017)☆10Jul 1, 2017Updated 9 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Stick Breaking Variational Autoencoder with HDP prior☆10Nov 29, 2017Updated 8 years ago
- ☆11Updated this week
- Co-training for Policy Learning☆13Aug 8, 2019Updated 7 years ago
- A penetration testing platform for ICS protocols and more☆12Jun 3, 2026Updated 5 months ago
- ☆12Jun 7, 2019Updated 7 years ago
- Deterministic Regular Expressions with Backreferences☆22Oct 12, 2020Updated 6 years ago
- An eBPF kernel Observable Agent To Spy Performance Issue On OS.☆13Oct 31, 2025Updated last year
- [ICRA 2024] WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection☆12Feb 6, 2024Updated 2 years ago
- This repo aims to offer a packet flow tracer based on bpf☆13Oct 6, 2019Updated 7 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Chaining of SR-aware and SR-unaware Service Functions☆10Apr 17, 2018Updated 8 years ago
- Benchmark Generator for Global Routing☆13Jul 18, 2019Updated 7 years ago
- ☆10Sep 12, 2024Updated 2 years ago
- Source code for our paper accepted for publication at USENIX NSDI 2022☆12Nov 7, 2022Updated 4 years ago
- nthu-route 2.11☆14Aug 5, 2019Updated 7 years ago
- PyTorch implementation of the Reinforced Mnemonic Reader + Answer Verifier model (https://arxiv.org/abs/1808.05759)☆10Nov 23, 2018Updated 7 years ago
- Datanlord's RDMA nic driver☆13Sep 12, 2024Updated 2 years ago
Are these results useful?