A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 19:30 UTC
[Bugfix] Fix logit soft cap in flash-attn backend (#7425)
Woosuk Kwon committed
Aug 12, 2024 at 09:58 UTC
cfba4def5d422dfbafbc21b8f695bdcb2295aa19
1 file changed
+1
vllm/attention/backends/flash_attn.py
+1
@@ -563,6 +563,7 @@ class FlashAttentionImpl(AttentionImpl):
563
softmax_scale=self.scale,
564
causal=True,
565
alibi_slopes=self.alibi_slopes,
566
+ softcap=self.logits_soft_cap,
567
).squeeze(1)
568
569
# Reshape the output tensor.