flashinfer-ai / flashinfer

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

doc: add some documentation for attention with mask API #271

Closed yzh119 closed 1 month ago

yzh119 commented 1 month ago

add fix the bugs in single_prefill_with_kv_cache and single_prefill_with_kv_cache_return_lse when using mask.