Qualify Spark output-head component on AMD NPU and update E2E matrix
This commit is contained in:
1 parent
10221f0665
commit
34295f3eb3
40 files changed
+3198
-4
No files matched your search
@@ -51,6 +51,8 @@ memory-accounting and unavailable-device gaps remain documented repair items.
|
||||
|
||||
### Mobile and PC × model support matrix
|
||||
|
||||
This section preserves the 2026-09-22 audit. For the latest per-cell disposition and 2026-09-23 follow-up evidence, use the [current 60-cell E2E matrix](../../benchmarks/edge_harness/results/e2e_profiling_20260922/evidence/summary/README.md). In particular, the HX370 AMD NPU now has a placement- and quality-verified **Spark 1.7B output-head component** through Omni, while complete Spark generation on that route remains unverified; see the [component record](../../benchmarks/edge_harness/results/e2e_expansion_20260923/evidence/spark_amd_npu_output_head/README.md). This advances the M3 component gate, not its whole-model or same-device handoff gate.
|
||||
|
||||
**All 60 named pairings were checked on 2026-09-22** through actual runs,
|
||||
raw-record review or artifact/runtime preflight. This is not 60 successful
|
||||
executions. Each cell links to its evidence, finding and next required step.
|
||||
|
||||
Reference in new issue
Block a user