Topic

amd

Repositories (1652)

archlinux-AMDVLK
archlinux-AMDVLK lodriguez Shell

PKGBUILDs to build stable AMDVLK-releases from source (amdvlk-git, lib32-amdvlk-git, amdvlk-bin)

2
HTML5-Game-AMD-TypeScript
HTML5-Game-AMD-TypeScript wildfirecode JavaScript

在基于TypeScript的LayaAir HTML5游戏开发中使用AMD

2
amd-rise
amd-rise rafaelcamargo JavaScript

Rise a lite AMD application in minutes

2
repkg
repkg privatenumber JavaScript

🚚 On-demand AMD npm package bundling service

2
threejs-controls
threejs-controls iondrimba JavaScript

Threejs Controls as modules (from examples folder)

2
Repeated-runs-become-slower-due-to-VRAM-offload-regression-with-DynamicVRAM-leak-spill-
Repeated-runs-become-slower-due-to-VRAM-offload-regression-with-DynamicVRAM-leak-spill- ElunaLevie

Observed during normal image generation. In our case, ComfyUI-N-Nodes / RIFE appears to keep GPU memory outside ComfyUI's model manager. Under heavier...

1
stats-hackintosh-patches
stats-hackintosh-patches Archibald-Lewis Python

AMD frequency and community NVIDIA metrics patches for Stats 3.0.23, plus a local JSON feed for VK03 Panel.

1
enterprise-rag-rocm
enterprise-rag-rocm vincenzo-afk

A multimodal Retrieval-Augmented Generation (RAG) pipeline for the AMD AI League. Features exact-set citations, VLM image parsing, and a persistent Un...

1
personaplex-rocm
personaplex-rocm HrMarcussen Python

Real-time full-duplex voice AI (NVIDIA PersonaPlex-7B) on AMD Radeon under native Windows: ROCm PyTorch + custom HIP kernels, 2.5x real time on an RX...

1
ComfyUI-H3-LatentAV
ComfyUI-H3-LatentAV enrand22 Python

Save/load MiniMax H3 audio+video (nested) latents in ComfyUI: the bridge for a two-pass H3 render on low-VRAM GPUs.

1
AMD-Pastis-Bartender
AMD-Pastis-Bartender Bemly Objective-C

AMD 歌词汉化下载器(液态玻璃风味)

1
quadri-image-studio
quadri-image-studio flaser381 TypeScript

Frontend for Qwen-Image-2.1 inference on AMD ROCm: text-to-image and image editing via headless ComfyUI, one-step installer for Linux and Windows

1
dlss5-webcam-demo
dlss5-webcam-demo aq0xs JavaScript

Demo DLSS 5 neural rendering on a live webcam, comparing skin, hair, and fabric quality side by side in real time.

1
amd-optical-sar-damage-review
amd-optical-sar-damage-review cool6boy Python

AMD ROCm云端光学–SAR建筑损毁分类与复核优先级研究|5476栋|跨事件评估、理想复核模拟与真实负结果

1
dartai
dartai ftoleedo Shell

Ternary LLMs on llama.cpp, any GPU — run a 27B model in 5.5–6.7 GB. Prebuilt Linux/Windows binaries, Vulkan and CUDA, OpenAI-compatible API.

1
strix-halo-windows-memory-fix
strix-halo-windows-memory-fix rahulrevolution06-design PowerShell

Windows memory-allocation fix for AMD Strix Halo / Ryzen AI Max+ 395 with 128 GB RAM: why gpt-oss-120b class models fail to load at a 96 GB VRAM carve...

1
rocm-windows-noinstall
rocm-windows-noinstall BearddOddity PowerShell

A HIP/ROCm build toolchain for consumer Radeon cards on Windows, assembled without installing anything and without touching the gaming driver. Verifie...

1
Cloud9-engine
Cloud9-engine GodsQuantum Python

Adaptive AMD RDNA inference runtime: benchmark Atomic + current llama.cpp, then promote the best backend safely.

1
strix-halo-jax
strix-halo-jax YauhenBichel Python

Run JAX and MuJoCo MJX on AMD Ryzen AI MAX (Strix Halo, gfx1151) from pip wheels - no system ROCm - with a hang-safe check that tells you which wheel...

1
boundary-amd-private-agent
boundary-amd-private-agent kaulastudies Python

Local-first private AI agent with deterministic permission and audit boundaries.

1
r9700-vllm-rocm72-fixes
r9700-vllm-rocm72-fixes FA85 Shell

Minimal AITER LDS and ROCr idle-CPU fixes for Radeon AI PRO R9700 on vLLM 0.29.0 / ROCm 7.2.3

1
amd-nvdiffrast-rocm72-gfx1201
amd-nvdiffrast-rocm72-gfx1201 Painter3000 Shell

Community ROCm 7.2 / RDNA4 gfx1201 patch stack for nvdiffrast. Non-commercial use restrictions may apply; see the NVIDIA Source Code License.

1
amd-boost-toggle
amd-boost-toggle rik-create3 Shell

A lightweight utility to toggle AMD CPU Boost on Linux — cooler thermals and quieter fans by default, full clocks on demand.

1
gatetrack-sentinel-amd-act-ii
gatetrack-sentinel-amd-act-ii Chatur27 Python

Human-governed visitor-risk operations with deterministic controls, bounded Fireworks AI review, audit trails and portable proof packets.

1
cursor-electronics
cursor-electronics monickverma Python

Circuit OS: AI hardware compiler. Plain English to validated schematic, Arduino firmware, SPICE simulation and BOM. Runs on AMD ROCm via vLLM.

1
bc250-cachyos-gaming
bc250-cachyos-gaming phantomwar PowerShell

Guia completo em PT-BR: AMD BC-250 (APU do PS5) para games com CachyOS - BIOS, ACPI, governor, unlock de 8 núcleos e 40 CUs, overclock, scripts e FAQ

1
swapchain-bottleneck
swapchain-bottleneck dantebuilds

Architecture analysis: why modern gaming still stutters — the missing overlay coordination layer in Windows (DXGI swapchain, MPO, DLL injection, TDR)....

1
hackintosh-amd-efi-bringup
hackintosh-amd-efi-bringup ArTreeChan Python

AMD 平台黑苹果(Hackintosh)OpenCore EFI 主线工作流技能:八步流程 + 8 份参考文档 + 6 个零第三方依赖的 Python 脚本

1
FusionFinance
FusionFinance TheOnlyFusionCube Python

Auditable hybrid ML and agentic trading research with evidence verification, portfolio risk controls, and AMD ROCm receipts.

1
Cloud9-embedding-engine
Cloud9-embedding-engine GodsQuantum Shell

RDNA-first OpenAI-compatible local embedding engine for llama.cpp

1
gfx1030-windows-pytorch
gfx1030-windows-pytorch Baiyu-Void Python

非官方实测:在 Windows 上让 AMD RX 6800 XT (gfx1030/RDNA2) 原生跑 PyTorch GPU 加速。含路线排除、8 条踩坑清单与自检脚本。

1
minisglang-rdna4
minisglang-rdna4 patcarter883 Python

OpenAI-compatible LLM server for AMD Radeon RX 9070 / 9070 XT (RDNA4). Native fp8/int4 WMMA — nothing dequantizes to fp16. One docker compose up.

1
BuffAdvisor
BuffAdvisor zero-abd Jupyter Notebook

BuffAdvisor (HackCU 2025): CU Boulder campus assistant running a Quark-quantized DeepSeek-R1-Distill-Llama-8B locally on an AMD AI PC, with RAG.

1
Qwen3.8-Flash-Next-EXL3-Framework-Strix-Halo-recipe
Qwen3.8-Flash-Next-EXL3-Framework-Strix-Halo-recipe vcruz305 Python

Run Qwen3.8-Flash-Next EXL3 (turboderp pack) on one AMD Strix Halo / Framework Desktop (gfx1151) via the exllamav3-amd runtime fork. 41 tok/s mean, 47...

1
ryzen-7900x-vfio-guide
ryzen-7900x-vfio-guide ekremx25 C#

AMD Ryzen 7900X / Raphael iGPU VFIO passthrough on Arch Linux: Windows 11 Code 43 reset workaround, Looking Glass, libvirt XML and VirtIO tuning

1
power-monitor
power-monitor matthewjdoyle Python

Real-time energy monitoring. Tracks CPU package, cores, uncore, DRAM, and platform total (PSYS) power at configurable intervals. Logs to SQLite, gener...

1
awesome-rdna
awesome-rdna 1337hero

A curated list of AI/LLM inference tools, builds, and guides for AMD RDNA GPUs (RX 7000/9000, Strix Halo, R9700)

1
ai-max-395-deploy
ai-max-395-deploy logandoo

An Agent-Skill that helps users deploy different models, including asr, tts, llm on AMD ai max 395

1
agentwish
agentwish fanzhiang Python

Qwen3.8-Flash-Next (qwen4exp) local deployment on AMD AI Max 395 — self-built llama.cpp/ROCm, OpenAI-compatible API, LM Studio-style console

1
FSR-4.0.2-reference
FSR-4.0.2-reference Rolaand-Jayz C++

Source forked from official AMD FSR 4.0.2

1
RigWatch
RigWatch danielemilushev-hub Python

Single-file Windows hardware monitor in Python — live CPU, RAM, per-GPU utilisation/VRAM/watts, disk I/O and PSU headroom. Built for multi-GPU AMD rig...

1
mingxin-kvcache-bench
mingxin-kvcache-bench mingxin-tech Python

Reproducible LLM KV-cache tiered-storage benchmark on AMD MI308X: LMCache parallel-read patch, load clients, orchestration, measured results

1
signalforge
signalforge rvbernucci Go

Private, local-first financial research agents on AMD Radeon and ROCm.

1
mojo-baro
mojo-baro amarbaro Mojo

Own inference stack on AMD gfx1100: Mojo GPU kernels, self-describing GGUF engine

1
ZoN-CreatorOS
ZoN-CreatorOS AlphaMaleBaDI Python

A Context-Native Creative Operating System that transforms persistent context into production-ready creative artifacts through intelligent agent orche...

1
perseus-amd-act-ii
perseus-amd-act-ii tcconnally Python

Perseus Vault x AMD Instinct — encrypted, local-first agent memory kept off the GPU. AMD Developer Hackathon Act II (Unicorn Track).

1
AnyDeck
AnyDeck neokura Python

Decky Loader plugin for turning AMD x86 SteamOS handhelds into a more Steam Deck-like experience

1
flashnext-rocm10-r9700
flashnext-rocm10-r9700 hazyumps Dockerfile

Experimental ROCm 10 compatibility build for Qwen3.8-Flash-Next on 4x AMD R9700

1
Modly-Turnaround
Modly-Turnaround bakahuiii Python

DirectML Image-to-3D workflow for Windows AMD GPUs, targeting Radeon RX 5000/6000/7000. End-to-end validated on RX 6750 GRE.

1
Lammps-Kokkos-MACE-single-GPU_LUMI
Lammps-Kokkos-MACE-single-GPU_LUMI ozakary

This repository documents how to build and run LAMMPS with the native PKG_ML-MACE interface for MACE machine learning force field simulations on the L...

1