fix: adds causal to attention params (#2408)

fix: adds causal to attention params to check when using flash attn v1
2024-08-13 10:19:46 -04:00 · 2024-08-13 10:19:46 -04:00 · 1cebccc72b
parent 59922f9bc1
commit 1cebccc72b
1 changed files with 1 additions and 0 deletions
--- a/server/text_generation_server/layers/attention/cuda.py
+++ b/server/text_generation_server/layers/attention/cuda.py
@ -293,6 +293,7 @@ else:
        max_s,
        softmax_scale,
        window_size_left=-1,
+        causal=None,
        softcap=None,
    ):
        if window_size_left != -1: