add ascend_310b deployment (README.md)

README.md

@@ -23,6 +23,7 @@ with two deployments sharing one contract.
 | deployment | backend | artifacts | notes |
 |---|---|---|---|
 | `ascend_310p` | Ascend ACL (Ascend310P1) | text_encoder + flow_decoder OM | fixed buckets (t256 / f1537), CFG-distilled 4-step |
+| `ascend_310b` | Ascend ACL (Ascend310B1) | text_encoder + flow_decoder OM (`*_310b_origin.om`) | 310B board-side synthesis |
 | `ubuntu_onnx` | ONNX Runtime CPU (torch profile) | dynamic-shape ONNX pair | host-side synthesis, 8-step default |
 
 Shared contract: `tensor_model/zipvoice/synthesize`
@@ -48,7 +49,8 @@ preprocessing `emilia-zh-cn2an-jieba-pypinyin-fixed-golden-prompt-v1`, output
 - `inference_manifest.json` — deployment routing (schema v3, iterative request contract)
 - `assets/zipvoice_310p.json` / `assets/zipvoice_onnx.json` — per-deployment runtime config
 - `assets/tokens.txt`, `assets/vocos/`, `assets/prompts/` — shared assets
-- `artifacts/ascend/ascend_310p/*.om` — compiled fixed-shape modules
+- `artifacts/ascend/ascend_310p/*.om` — compiled fixed-shape modules (310P)
+- `artifacts/ascend_310b/*.om` — compiled fixed-shape modules (310B)
 - `artifacts/onnx/*.onnx` — dynamic-shape ONNX exports
 
 ## Usage