add ascend_310b deployment (README.md)

README.md

@@ -24,6 +24,7 @@ deployments sharing one stream contract.
 | deployment | backend | artifacts | notes |
 |---|---|---|---|
 | `ascend_310p` | Ascend ACL (Ascend310P1) | stateful FB/SB OM pair | board-side streaming (LSTM state via state_links) |
+| `ascend_310b` | Ascend ACL (Ascend310B1) | stateful FB/SB OM pair (`*_310b_origin.om`) | 310B board-side streaming |
 | `torch_cuda` | PyTorch CUDA | — (ckpt in `assets/`) | host-side streaming executor |
 | `torch_cpu` | PyTorch CPU | — (ckpt in `assets/`) | CPU fallback (watch the 128 ms hop budget) |
 
@@ -50,7 +51,8 @@ step.
 - `inference_manifest.json` — deployment routing (schema v3, stateful stream contract)
 - `assets/adapter.json` — algorithm contract (STFT 512/256, T=2, look-ahead 2)
 - `assets/cum_fullsubnet_best_model_218epochs.tar` — Torch checkpoint
-- `artifacts/ascend/fullsubnet/*.om` — stateful FB/SB OM modules
+- `artifacts/ascend/fullsubnet/*.om` — stateful FB/SB OM modules (310P)
+- `artifacts/ascend_310b/fullsubnet/*.om` — stateful FB/SB OM modules (310B)
 
 ## Usage