Skip to content

v1.2.0 — Portable Native AMD395 Runtime

Choose a tag to compare

View all tags
@skyguan92 skyguan92 released this 23 Jul 08:38
· 368 commits to main since this release
v1.2.0
e430e50

Highlights

  • Self-contained portable native runtime for AMD Ryzen AI Max+ 395 / gfx1151.
  • One static aima-engine entry point with a bundle-local ROCm userspace closure.
  • No host Python, PyTorch, vLLM, Triton, Transformers, or system ROCm userspace installation is required.
  • Resident OpenAI-compatible HTTP service, exact-prefix cache reuse, native tokenizer, direct Safetensors loading, and graceful shutdown.

Qualification

  • 19/19 batch-1 performance cells passed the frozen >=0.97x retention gate.
  • Minimum cold-prefill retention: 1.0109x; minimum decode retention: 0.9740x.
  • 9/9 full-vocabulary correctness contexts passed; maximum KLD 0.002174 < 0.005, with top-1 agreement in every context.
  • Exact 128-token identity passed at 8K context.
  • Median command-to-ready startup: 42.52 s.
  • 32K exact-prefix hit TTFT: 9.195 ms versus 24.22 s cold (2634x), with 1.0006x decode retention.
  • Fresh extracted-bundle full-model smokes passed at 1K, 16K, and 64K.

Runtime boundary

The model weights are not included. The runtime requires Linux x86-64, the AMDGPU/KFD kernel driver and render nodes, an AMD gfx1151 GPU, and a separately obtained Qwen3.6-35B-A3B-BF16 checkpoint.

Integrity

Archive SHA-256: 3bfe25c49b7edb29853a821267220e9c4f7025685aa4e423605ee43e8b240672

sha256sum -c aima-engine-native-portable-805b34f5fe6f.tar.zst.sha256
Assets 4
Loading