pendulum445

co_http

小彭老师特意从零开始研发的一款教学用，基于 C++17 回调函数的异步 HTTP 服务器

cppguidebook

小彭老师领衔编写，现代C++的中文百科全书

KGAUnlearn

OSD

REST

REST: Retrieval-Based Speculative Decoding, NAACL 2024

axolotl

Go ahead and axolotl questions

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

swift-style-guide

The official Swift style guide for Kodeco.

Kangaroo

Implementation of Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

LLMSpeculativeSampling

Fast inference from large lauguage models via speculative decoding

marktext

📝A simple and elegant markdown editor, available for Linux, macOS and Windows.

Spec-Bench

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)

suying666

速鹰666官网登录地址

json

JSON for Modern C++

flash-attention

Fast and memory-efficient exact attention

Xiaomi_Kernel_OpenSource

Xiaomi Mobile Phone Kernel OpenSource

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

AlamofireImage

AlamofireImage is an image component library for Alamofire

Speculative-Sampling

Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind

LookinServer

Free macOS app for iOS view debugging.

HITSZ-OpenCS

哈尔滨工业大学（深圳）计算机专业课程攻略 | Guidance for courses in Department of Computer Science, Harbin Institute of Technology (Shenzhen)

cs-roadmap

❤️这是一条汇总网上许多资料，而不是资料的纯粹堆砌，让人眼花缭乱的复制粘贴，这不是帮你在总结所有的知识点，而是根据实际的计算机系课程来安排学习路线，并且配合上面向就业的学习，与完全跟着学校课程相比，做到了不和工业界面试不脱节，非常实际、非常认真、非常掉头发，真心求个视频三连！