ORT MatMulNBits on SpaceMiT X60 (K1) — real LLM decode via IME

We got ONNX Runtime’s int4/int8 MatMulNBits path running on the Orange Pi RV2 through MLAS CompInt8 + smt.vmadot. Decode (ms/token, lower better):

Model Quant @4 threads
Qwen2.5-0.5B int4 ~80 ms
Qwen2.5-0.5B int8 ~159 ms
SmolLM2-360M int4 ~80 ms
SmolLM2-360M int8 ~140 ms
TinyLlama-1.1B int4 ~156 ms

Qwen used to sit at ~16 s/tok on the wrong path (CompFp32). With accuracy_level=4 + pack/panel kernels that’s ~80 ms int4 and ~159 ms int8 @4t.

Story (results first, then how): ONNX Runtime on X60 — real LLM decode via IME MatMulNBits | OpenSolvers
Code: https://github.com/opensolvers/benchmarks/tree/main/onnx

1 个赞