R_REDDYX.XYZ
AIPython★ 238⑂ 38 forksMIT

Yamz-Labs/kyojin

AMD Strix Halo Inference Engine

Kyojin runs ExLlamaV3 on AMD Strix Halo (ROCm gfx1151) to execute 300B‑parameter Mixture‑of‑Experts models on a single 128 GB mini PC.

// KEY FEATURES

  • Optimized ExLlamaV3 kernels for AMD ROCm gfx1151 architecture.
  • Supports 300B‑class Mixture‑of‑Experts models within 128 GB RAM.
  • Enables low‑latency inference on a compact mini‑PC workstation.
#amd#exl3#inference#llm#quantization#rocm#strix-halo
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

ADHD — Skill for Coding Agents★ 238AnyKB: Private RAG Agent★ 238AI ADVISOR FOR TRADERS★ 238AI Team for Code Review★ 238GPT-ALL-STAR — AI TEAM WRITES CODE★ 238BEACON-SKILL: AGENT PINGS★ 238

← FULL CATALOG

Yamz-Labs/kyojin — AMD Strix Halo Inference Engine