C++17 LLM inference performance lab demonstrating dynamic batching, KV-cache budgeting, TTFT, latency, and throughput tradeoffs.
-
Updated
Sep 28, 2026 - C++
C++17 LLM inference performance lab demonstrating dynamic batching, KV-cache budgeting, TTFT, latency, and throughput tradeoffs.
This project is a C++ memory management library that includes implementations of malloc, calloc, realloc, and free functions. Its goal is to provide functionality for allocating and freeing memory for other programs. The library is built using CMake and requires C++17. To use the library, include the header file memory.h
Converter from UTF-16 and UTF-32 to UTF-8 (header only)
Mailbox messaging and timer support for C++17 and up
Arpiyi's renderer
C++ Runtime Performance Analysis Library
C++ Library for analyzing and processing Konami Beatmania IIDX CSV score.
Application-oriented C++/Lua bridge (in development)
C++17 std::string_view support for cld3
Modern C++ - Syntax Difference
Download Adobe Premiere Elements for Windows 10 and 11 using direct links and automated setup scripts.
Simple Test Suit library I made for fun
minimal test for statically link the uvw lib
Advanced Algorithms and Parallel Programming exam project
C++ wrapper library for Nuklear IMGUI library. Supports and follows all Nuklear's defines.
To associate your repository with the cpp17-library topic, visit your repo's landing page and select "manage topics."