rocm repositories

Trending repositories tagged rocm, ranked by trending score. Updated daily.

  1. 1
    mw00/project-maya

    Run GLM-5.3 (744B), DeepSeek-V4.1-Flash (748B), MiniMax-M3.1-Flash (428B), GLM-5.3-Flash (321B) and Hy4-Flash (220B) on your own GPUs - from 8 GB of VRAM, NVIDIA and AMD, one dashboard, OpenAI- and Anthropic-compatible API.

    GitHub · C++ · 3,120 stars · 435 forks · +69 stars in 24 hours · Trending score 3.63

  2. 2
    wici-ai/inferssd

    Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

    GitHub · C++ · 1,274 stars · 114 forks · +32 stars in 24 hours · Trending score 3.48

  3. 3
    peonist-ai/halogen-flash-server

    Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

    GitHub · Shell · 1,407 stars · 102 forks · +17 stars in 24 hours · Trending score 2.66

  4. 4
    LMCache/LMCache

    LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

    GitHub · Python · 12,400 stars · 2,171 forks · +18 stars in 24 hours · Trending score 2.63

  5. 5
    SemiAnalysisAI/InferenceX

    Open Source AI Accelerator Research Platform Standard / 开源推理研究平台

    GitHub · Python · 2,072 stars · 384 forks · +15 stars in 24 hours · Trending score 2.47

  6. 6
    tracel-ai/burn

    Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

    GitHub · Rust · 16,315 stars · 1,137 forks · +14 stars in 24 hours · Trending score 2.41

  7. 7
    lemonade-sdk/lemonade

    Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

    GitHub · C++ · 6,259 stars · 571 forks · +8 stars in 24 hours · Trending score 2.23

  8. 8
    hiruhiru2005/sync-strata

    A one-click local LLM app for Windows and Linux: Qwen3.8-Flash-Next with the Sync quantizations (XS, S, M), based on Strata.

    GitHub · C++ · 75 stars · 7 forks · +48 stars in 24 hours · Trending score 2.14

  9. 9
    ahtx/kindi

    Kindi 0.6.1: fast local LLM inference on low-cost GPUs and CPUs. DeepSeek-V4.1-Flash (552B) at 18.7 tok/s on one RTX 3060 12 GB with a dual-Xeon DDR4 server. Ternary Bonsai 2B-27B, AH-Nanbeige4.3-33B, Nemotron 3.5 Lightning 30B-A3B. NVIDIA from the Quadro K420 to the RTX 50 series, AMD Radeon graphics, Windows and Linux. OpenAI-compatible server.

    GitHub · Python · 195 stars · 41 forks · +6 stars in 24 hours · Trending score 1.95

  10. 10
    AMD-AGI/Hyperloom

    An agentic system that auto-optimizes LLM workloads on AMD GPUs.

    GitHub · Python · 282 stars · 89 forks · +7 stars in 24 hours · Trending score 1.88

  11. 11
    stew675/llama-cpp-rdna-boosts

    A set of performant RDNA/HIP patches against llama.cpp focusing on high speed inferencing with numerics assurance

    GitHub · Shell · 273 stars · 24 forks · +6 stars in 24 hours · Trending score 1.86

  12. 12
    warpfront/hipfire

    RDNA-native LLM inference engine in Rust.

    GitHub · Rust · 819 stars · 109 forks · +5 stars in 24 hours · Trending score 1.64

  13. 13
    Luce-Org/lucebox

    Lucebox inference engine for heterogeneous hardware & consumer GPUs

    GitHub · C++ · 3,023 stars · 299 forks · +3 stars in 24 hours · Trending score 1.63

  14. 14
    iree-org/iree

    A retargetable MLIR-based machine learning compiler and runtime toolkit.

    GitHub · C++ · 4,023 stars · 1,065 forks · +4 stars in 24 hours · Trending score 1.61

  15. 15
    hec-ovi/vllm-awq4-qwen

    vLLM Qwen 3.6-27B (AWQ-INT4) + DFlash speculative decoding on AMD Strix Halo (gfx1151 iGPU, 128 GB UMA, ROCm 7.13). 24.8 t/s single-stream, vision, tool calling, 256K context, OpenAI-compatible, Docker. Matches DGX Spark FP8+DFlash+MTP at a third of the cost. No CUDA.

    GitHub · Python · 53 stars · 5 forks · +8 stars in 24 hours · Trending score 1.60

  16. 16
    SlyBase/vllm-sly-radiance

    Working on the fastest vllm path for AMD Radeon AI PRO R9700

    GitHub · Python · 117 stars · 11 forks · +6 stars in 24 hours · Trending score 1.49

  17. 17
    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.

    GitHub · C++ · 38 stars · 6 forks · +4 stars in 24 hours · Trending score 1.48

  18. 18
    jaedync/crucible-strix-halo

    Run Qwen3.8-Flash-Next on one AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). EXL3 4.05 and 3.05 bpw packs, own ROCm/HIP kernels, OpenAI-compatible server, 4 sessions of 262K context, setup guide included.

    GitHub · Python · 35 stars · 7 forks · +2 stars in 24 hours · Trending score 1.45

  19. 19
    IIIIIllllIIIIIlllll/Qwenox

    An inference framework customized for AI MAX 395, compatible with both Linux and Windows, and supports deploying only qwen3.8-flash-next. This project is for reference and learning purposes only. 为AI MAX 395定制的推理框架,Linux和Windows通用,只能部署qwen3.8-flash-next。本项目仅供参考学习使用。

    GitHub · C++ · 150 stars · 31 forks · +5 stars in 24 hours · Trending score 1.45

  20. 20
    Motphys/Uni-SuperMimic

    SuperMimic-UniLab: An Independent reproduction of SuperMimic on UniLab for whole-body humanoid motion tracking.

    GitHub · Python · 312 stars · 25 forks · +1 stars in 24 hours · Trending score 1.21

  21. 21
    ROCm/AMDMIGraphX

    AMD's graph optimization engine.

    GitHub · C++ · 341 stars · 168 forks · +2 stars in 24 hours · Trending score 1.19

  22. 22
    JMS1717/ming-voice

    Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux

    GitHub · Python · 451 stars · 26 forks · +3 stars in 24 hours · Trending score 1.15

  23. 23
    ModelCloud/GPTQModel

    LLM model quantization (compression) toolkit with HW acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU, Tenstorrent, Huawei Ascent NPU, and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

    GitHub · Python · 1,294 stars · 221 forks · +2 stars in 24 hours · Trending score 1.11

  24. 24
    pantheongpu/pantheonsim

    PantheonSim: GPU simulator for CUDA and ROCm. Run CUDA and HIP programs unmodified on a CPU, no GPU needed: simulated NVIDIA and AMD GPUs for development, teaching and CI.

    GitHub · C++ · 43 stars · 7 forks · +1 stars in 24 hours · Trending score 0.97