flashinfer-ai / flashinfer

FlashInfer: Kernel Library for LLM Serving
https://flashinfer.ai
Apache License 2.0
768 stars 64 forks source link

doc: fix the description of logits cap in docstring #299

Closed yzh119 closed 3 weeks ago

yzh119 commented 3 weeks ago

The logits cap was applied to pre-attention logits, not attention scores.