Topic

amd

Repositories (1652)

Vega56-64-MacOs-LLAMA.CPP-Launcher
Vega56-64-MacOs-LLAMA.CPP-Launcher bagueDev Python

Web-basierter Launcher für llama.cpp mit eGPU Support --LLAMA.CPP · VULKAN · AMD RX VEGA 56/64 Launcher

1
nemotron-3.5-30b-a3b-rocmfp4
nemotron-3.5-30b-a3b-rocmfp4 julianmb Shell

Converter fixes, NVFP4 findings & Strix Halo ROCmFP4 benchmarks for NVIDIA Nemotron 3.5 Lightning 30B-A3B

1
AMD-AI-COMPASS
AMD-AI-COMPASS Maxritz Python

AI Compute Performance Analysis & Statistics Suite - RDNA4 AI Compute Toolset for Windows

1
amd-gpu-fan-curve
amd-gpu-fan-curve HarukaYamamoto0 C#

A Windows desktop application for creating and applying custom fan speed curves to AMD GPUs. Built with WPF and WPF UI (Fluent)

1
llmsetup
llmsetup c4software Shell

Pilote un llama-server en router mode natif sur Strix Halo : modeles GGUF, models.ini genere, bench API, tuning MTP, service systemd

1
Prog-Language-Eggs
Prog-Language-Eggs PotenFYR-Studios Shell

One egg. One image. Every language. A production-grade hosting platform that installs, updates, compiles and runs 50+ programming languages inside you...

1
ASCCelsync
ASCCelsync eloyssync Python

High-performance shader cache and temporary app artifact cleaner built with PyQt6

1
remora-lab
remora-lab leoinfer Rust

Local-AI systems research: making large, sparse MoE models practical on constrained consumer hardware. Representation, MoE residency, VRAM/RAM/NVMe ti...

1
Adrenalin-logs
Adrenalin-logs deftmousetail HTML

Explore AMD Adrenalin Hardware, FPS/Latency, and FrameTime logs. Runs entirely locally in your browser—your logs are never uploaded.

1
Crux
Crux Enoch208 Python

Find how a robot fails. Repair it. Prove it. Failure discovery → repair → statistical qualification for contact-rich manipulation, end to end on one A...

1
rocm-scribe
rocm-scribe iaintheardofu Python

Automated CUDA-to-ROCm GPU kernel translation via semantic BridgeIR. 316 HIP API mappings, wavefront-aware optimization, MFMA targeting, 6 multi-targe...

1
LollozzOs_Configurator
LollozzOs_Configurator LollozzOS

LollozzOS Configurator is a utility I created (Lollozz) that includes all the tweaks and operations needed to simplify and optimize Windows 10/11. Eac...

1
Autonomous-SRE-Self-Healing-Cloud-Guardian
Autonomous-SRE-Self-Healing-Cloud-Guardian monsiu Python

Aegis is an AI-powered SRE tool that monitors cloud infrastructure, detects incidents, diagnoses issues, and performs automated remediation through a...

1
durden-ec
durden-ec Gourav-334 C

DEC (Durden’s Engine Collection) is a modular suite of source-to-memory tools for system-level programming. Originally developed as MALTOSE, DEC is ev...

1
mi350p-gpu-fleet-automation
mi350p-gpu-fleet-automation PoisonOakey

[Case Study] A highly concurrent, config-driven fleet installer for managing drivers and runtimes across 20+ enterprise bare-metal AMD Instinct™ MI350...

1
Strix-Halo-Linux-Llama_cpp-ROCm
Strix-Halo-Linux-Llama_cpp-ROCm LucRoot

Production ROCm llama.cpp build recipe for AMD Strix Halo (gfx1151, Ryzen AI MAX+ 395) — plus seven-model serving runbooks, KV-cache sizing against a...

1
TempoDAG
TempoDAG 1509Chamma Python

Compiler for streaming time-series models on FPGAs: hardware costs predicted before synthesis, certified against machine-checked scheduling theorems (...

1
WhisperWriter-AMD
WhisperWriter-AMD storm-ace Python

WhisperWriter fork with a whisper.cpp + Vulkan GPU engine for AMD GPUs/iGPUs on Windows (where faster-whisper/CUDA can't run). Dictate with Whisper la...

1
linux-rcraid-nvme-raid0
linux-rcraid-nvme-raid0 wickist Shell

AMD rcraid Linux 6.14 DKMS port, NVMe RAID0 setup, mdadm/XFS tuning and fio benchmarks for high-speed workstation storage.

1
amdtop
amdtop zyoung11 C++

AMD GPU monitor for Linux and Windows with a terminal UI

1
unsloth-rocm-libhsa-fix
unsloth-rocm-libhsa-fix boundring Shell

Workaround for a vendor-side bug: Unsloth Studio's bundled llama.cpp prebuilt ships libhsa-runtime64.so.1 (1.21.x) which segfaults on AMD RDNA 3 GPUs....

1
team-red-llm
team-red-llm serranoid Shell

Running LLMs locally on AMD GPUs, by people who actually do it. Cookbook + benchmark database for ROCm/HIP inference on Radeon, Instinct, and Strix Ha...

1
vramwatch
vramwatch RamazanKara Go

The flame graph for "why won't this model fit": live-trace local-LLM VRAM (weights vs KV cache) and predict max context before OOM. Zero-dependency Go...

1
amd-hackathon
amd-hackathon thassan1977 Rust

AEGIS is a self-evolving WAF: when an attack slips past every static rule, an AMD GPU-hosted LLM proposes a new signature, a deterministic Rust engine...

1
Sentra
Sentra Nattawat1409 Python

Autonomous predictive maintenance intelligence powered by 3 AI agents on AMD MI300X GPU

1
comfyui-amd-plug-and-play
comfyui-amd-plug-and-play miradorventus Shell

Plug-and-play installer for ComfyUI on AMD GPUs (Ubuntu/Mint). ROCm setup, AllTalk/Wan2.2 workflows ready, on-demand launcher.

1
zenstates-go
zenstates-go zhenruyan Go

AMD Ryzen processor overclocking toolkit — rewritten in Go with beautiful terminal display.

1
GreatAegis
GreatAegis zulroxx TypeScript

Post-quantum secure enterprise AI gateway featuring client-side PQC encryption, dynamic hybrid workload routing, and isolated open-source LLM inferenc...

1
AI-Quant-Coder
AI-Quant-Coder AghaEssa Python

An end-to-end Financial Market Predictor and Retrieval-Augmented Generation (RAG) Coding Assistant powered by open-source LLMs on AMD Developer Cloud...

1
Kipp
Kipp Polished-Snow C

Kipp — A small, hand-written inference engine for a single model family on local hardware.

1
anywhere-agents
anywhere-agents montgomeryunpopular607 Python

Manage agent configurations across projects with a single AGENTS.md file to standardize rules, skills, and permissions for any LLM-powered tool.

1
qwen-visual-training-lab
qwen-visual-training-lab I2evard Python

Windows-native AMD + DirectML lab for Qwen-style visual LoRA experiments.

1
ollama-amd-plug-and-play
ollama-amd-plug-and-play miradorventus Shell

Plug-and-play installer for Ollama + Open WebUI on AMD GPUs. ROCm setup, ComfyUI/AllTalk-compatible, zenity-driven UX.

1
class-notes-mcp
class-notes-mcp Charly-bite Python

"Modular Python system for recording, transcribing, and generating class notes."

1
marrow
marrow nssriraam Python

An AI-powered command center that correlates AWS FinOps data with SecOps vulnerabilities using Fireworks AI and AMD Instinct MI300X.

1
voice-to-text
voice-to-text powell-clark Rust

Push-to-talk transcription using local OpenAI Whisper models with Vulkan/Metal GPU acceleration. Free, fast and accurate with LTS support for Windows,...

1
Sovereign-Engine
Sovereign-Engine corbac10099 C++

Ultra-fast LLM inference engine — Vulkan backend, no CUDA required, AMD/Intel/NVIDIA

1
npu-embeddings
npu-embeddings jyatesdotdev Python

Text embeddings on AMD XDNA NPU (Strix Halo) — OpenAI-compatible /v1/embeddings endpoint powered by all-MiniLM-L6-v2 running on the NPU tile array

1
gaff
gaff CBailey589 Python

Automatically detects your GPU and installs the correct version of PyTorch for your environment.

1
rx9060xt-llm-benchmarks
rx9060xt-llm-benchmarks parsapp Shell

llama.cpp benchmarks on AMD RX 9060 XT 16GB — Vulkan vs ROCm (Linux)

1
expertmesh
expertmesh manishklach Python

Low-cost AMD/ROCm stationary-expert fabric for configurable trillion-parameter sparse MoE inference, with packed-INT4 HIP kernels, activation-only RoC...

1
ComfyUI-StrixHalo
ComfyUI-StrixHalo wabibito Shell

ComfyUI for AMD Strix Halo (gfx1151) on Ubuntu 26.04 via distrobox + rootless podman

1
repomind-v3
repomind-v3 SRKRZ23 HTML

On-prem AI coding agent + LLM cost-router for regulated enterprises — 100% AMD, open-weight, air-gapped, Ed25519 tamper-evident audit. AMD ACT I 1st-p...

1
lysergic-ai-control-plane
lysergic-ai-control-plane popdeuxrem TypeScript

Operational control plane for reliable AI execution built with FastAPI, Next.js, Docker and Fireworks AI on AMD infrastructure.

1
MangaOCR-Overlay
MangaOCR-Overlay Fluue JavaScript

Browser overlay that turns Japanese manga into invisible, selectable text for Yomitan dictionary lookups.

1
cscaler
cscaler CRTYPUBG C++

CScaler bridges upscaling/frame gen across GPUs. Supports DLSS2+/XeSS/FSR2+ inputs, replaces native upscalers, enables FSR-FG/XeFG on non-FG titles. S...

1
thermal-observatory
thermal-observatory manishklach C

A generic thermal observability framework for CPU, GPU, board, and platform telemetry across vendor APIs, kernel interfaces, and runtime correlation l...

1
rocm-bench-toolkit
rocm-bench-toolkit denisofyan Python

Zero-config LLM benchmarking on AMD GPUs with ROCm. Auto-detect MI300X/MI250/Radeon, CUDA and CPU fallback.

1
codeverse-personal-python
codeverse-personal-python marlinagency Python

Compiler-backed personalized Python learning with real execution and graduation to standard syntax.

1
codex-windows-memory-leak-investigation
codex-windows-memory-leak-investigation TangAnNing PowerShell

Windows memory exhaustion investigation and monitoring tools for Codex Desktop.

1