unified-memory 开源项目推荐（76 个）

hogeheer499-commits /strix-halo-guide

AMD Strix Halo本地LLM指南：为Ryzen AI MAX+ 395 / Radeon 8060S、Ollama、llama.cpp Vulkan/RADV、ROCm、原始证据、直接100 t/s 30B Qwen、140 t/s CHADROCK MTP、120B GGUF。

duongngocbinh56599-ui /local-llm-lab

Honest local LLM deployment planning and benchmarking for high unified-memory Macs and future Linux/NVIDIA rigs.

denoflore /greenboost-windows

Windows port of GreenBoost - GPU VRAM extension with system RAM & NVMe for larger LLMs. Original by Ferran Duarri (GPL v2).

parallelArchitect /sparkview

Operator-grade GPU monitor for NVIDIA GPUs with native GB10 / DGX Spark coherent UMA support — PSI pressure, clock detection, ConnectX-7 network layer

raspoli /mlx-serve

Local inference server for Apple Silicon — hot-swaps MLX models (LLM, vision, embeddings, TTS, STT) via OpenAI API

hyukudan /strix-halo-engine-lab

Exact LLM inference engine written from scratch for AMD Strix Halo (gfx1151, ROCm/HIP). Qwen3.8-Flash-Next on one node or two replicas; DeepSeek V4.1 Flash across two nodes over USB4 with an optional RTX PRO. Speculative decoding bit-identical to greedy, up to 255 tok/s on coding chat. MiniMax and GLM next.

singhpratech /ArrowMetal

Apache Arrow compute on Apple silicon GPUs through Metal: Arrow columns in unified memory, copy-free where the producer's buffers are page aligned; null-aware GPU kernels; Arrow C Data, C Device and C Stream interop

real-space /tfQMRgpu

A CUDA implementation of the transpose-free Quasi-Minimal Residual method

hamtun24 /openuma

Unified Memory Abstraction Layer for AI Inference on AMD APUs and Intel iGPUs

kaka86mm /TitanVault

A turnkey, fully-local AI workstation engineered for the AMD Ryzen AI Max+ 395. LLM inference, voice, document parsing, browser automation, agents — all on-device.

parallelArchitect /cuda-unified-memory-analyzer

gpu thrashingNVIDIA GPU Unified Memory diagnostic tool — architecture-aware, measurement-based, PCIe/coherent transport detection

ChrisJR035 /Talos-O-Architecture

Talos-O (Omni): A sovereign, embodied agentic organism forged on AMD Strix Halo. Integrating the Chimera Kernel (Linux 7.0), Zero-Copy Introspection, and the Phronesis Engine. Built from First Principles.

Graphene-Lab /Ryzen-AI-Max-395-SUPERFAST

SUPERFAST: turn an AMD Ryzen AI Max+ 395 (Strix Halo, gfx1151) into a fast, private local-LLM machine. Four profiles at maximum context: Qwen3.8-27B dense, Qwen3.8-Flash-Next MoE, Gemma-4-26B, DeepSeek-V4-Flash. Fedora 44 setup script, verified downloads, one-command switch, agent-ready API.

shumbul /Accelerated-Computing

Fundamentals of Accelerated Computing C/C++ is a course provided by NVIDIA.

parallelArchitect /gb10-kernel-probe

Empirical kernel scheduling characterization for NVIDIA GB10 (SM121a). Sweeps GEMM tile configurations, classifies PTX instruction paths, captures hardware telemetry

c0deJedi /llm-fit

Research into CUDA Unified Memory as a VRAM extension for LLM inference

CINOAdam /nvml-unified-shim

NVML unified memory shim for NVIDIA DGX Spark Grace Blackwell GB10 - enables MAX Engine, PyTorch, and GPU monitoring

NextTokens /WayInfer

Run LLMs larger than your RAM — native GGUF inference engine with SSD streaming, no GPU required

tcclaviger /systop

System monitor that reports real GPU memory on unified-memory AMD parts (Strix Halo / Ryzen AI Max), where other tools show only the firmware carve-out. Split collector daemon + TUI, no dependencies.

suraj-phanindra /datum

The real-time coordination layer for teams of developers running Claude Code agents. Git coordinates code at rest; Datum coordinates agents in motion.