[Optimization] support bladedisc fp16 optimization (#1790)

xiaowan0322

2024-06-06 9a9b474e7de7cc90d2ee124dc8d6c2cfa887c059

 funasr/models/sense_voice/decoder.py

@@ -146,7 +146,9 @@
                qk = qk + mask[:n_ctx, :n_ctx]
            else:
                mask = mask.unsqueeze(1).eq(0)  # (batch, 1, *, time2)
                min_value = float(np.finfo(torch.tensor(0, dtype=qk.dtype).numpy().dtype).min)
                min_value = -float(
                    "inf"
                )  # min_value = float(np.finfo(torch.tensor(0, dtype=qk.dtype).numpy().dtype).min)
                qk = qk.masked_fill(mask, min_value)

        qk = qk.float()