From 9a9b474e7de7cc90d2ee124dc8d6c2cfa887c059 Mon Sep 17 00:00:00 2001
From: xiaowan0322 <wanchen.swc@alibaba-inc.com>
Date: 星期四, 06 六月 2024 15:59:56 +0800
Subject: [PATCH] [Optimization] support bladedisc fp16 optimization (#1790)
---
funasr/models/sanm/attention.py | 18 +++++++++++++-----
1 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/funasr/models/sanm/attention.py b/funasr/models/sanm/attention.py
index da8850f..c7e8a8e 100644
--- a/funasr/models/sanm/attention.py
+++ b/funasr/models/sanm/attention.py
@@ -100,7 +100,9 @@
n_batch = value.size(0)
if mask is not None:
mask = mask.unsqueeze(1).eq(0) # (batch, 1, *, time2)
- min_value = float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
+ min_value = -float(
+ "inf"
+ ) # float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
scores = scores.masked_fill(mask, min_value)
self.attn = torch.softmax(scores, dim=-1).masked_fill(
mask, 0.0
@@ -269,7 +271,9 @@
mask = mask.unsqueeze(1).eq(0) # (batch, 1, *, time2)
- min_value = float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
+ min_value = -float(
+ "inf"
+ ) # float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
scores = scores.masked_fill(mask, min_value)
self.attn = torch.softmax(scores, dim=-1).masked_fill(
mask, 0.0
@@ -673,7 +677,9 @@
n_batch = value.size(0)
if mask is not None:
mask = mask.unsqueeze(1).eq(0) # (batch, 1, *, time2)
- min_value = float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
+ min_value = -float(
+ "inf"
+ ) # float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
# logging.info(
# "scores: {}, mask_size: {}".format(scores.size(), mask.size()))
scores = scores.masked_fill(mask, min_value)
@@ -774,7 +780,7 @@
return q, k, v
def forward_attention(self, value, scores, mask, ret_attn):
- scores = scores + mask
+ scores = scores + mask.to(scores.device)
self.attn = torch.softmax(scores, dim=-1)
context_layer = torch.matmul(self.attn, value) # (batch, head, time1, d_k)
@@ -858,7 +864,9 @@
mask = mask.unsqueeze(1).eq(0) # (batch, 1, *, time2)
- min_value = float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
+ min_value = -float(
+ "inf"
+ ) # float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
scores = scores.masked_fill(mask, min_value)
self.attn = torch.softmax(scores, dim=-1).masked_fill(
mask, 0.0
--
Gitblit v1.9.1