runanywhere

/

nv_embedqa_1b_HNPU

like 0

Follow

RunAnywhere, Inc. 19

Adds a v79/ bundle (Hexagon v79 / SM8750, Galaxy S25, soc_model 69) alongside the existing arch dirs. Compiled with QAIRT 2.48. Nothing under v75/ or v81/ is touched.

Device validation — SM8750 / v79

device-vs-HF cosine 0.999998 (worst of 6).

Validated on a real Galaxy S25 via QHexRT Plane A (qhx_asr / qhx_embed / qhx_generate). Full record, build recipe and gotchas: forge/recipes/nvidia/*/results/device_v79.json.

Gate B (raw-I/O parity) has not been run for this model on this arch; the accuracy evidence above is end-to-end plus the offline export gates.