提交 f4b2d469 编写于 作者: V Varuna Jayasiri

fix

上级 eb92824e
......@@ -602,7 +602,7 @@
<span class="lineno">173</span> <span class="n">k</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">to_k</span><span class="p">(</span><span class="n">cond</span><span class="p">)</span>
<span class="lineno">174</span> <span class="n">v</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">to_v</span><span class="p">(</span><span class="n">cond</span><span class="p">)</span>
<span class="lineno">175</span>
<span class="lineno">176</span> <span class="nb">print</span><span class="p">(</span><span class="s1">&#39;use flash&#39;</span><span class="p">,</span> <span class="n">CrossAttention</span><span class="o">.</span><span class="n">use_flash_attention</span><span class="p">)</span>
<span class="lineno">176</span> <span class="nb">print</span><span class="p">(</span><span class="s1">&#39;use flash&#39;</span><span class="p">,</span> <span class="n">CrossAttention</span><span class="o">.</span><span class="n">use_flash_attention</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">flash</span><span class="p">)</span>
<span class="lineno">177</span>
<span class="lineno">178</span> <span class="k">if</span> <span class="n">CrossAttention</span><span class="o">.</span><span class="n">use_flash_attention</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">flash</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">cond</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_head</span> <span class="o">&lt;=</span> <span class="mi">128</span><span class="p">:</span>
<span class="lineno">179</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">flash_attention</span><span class="p">(</span><span class="n">q</span><span class="p">,</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span>
......
......@@ -173,7 +173,7 @@ class CrossAttention(nn.Module):
k = self.to_k(cond)
v = self.to_v(cond)
print('use flash', CrossAttention.use_flash_attention)
print('use flash', CrossAttention.use_flash_attention, self.flash)
if CrossAttention.use_flash_attention and self.flash is not None and cond is None and self.d_head <= 128:
return self.flash_attention(q, k, v)
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册