Fix the type of `paged_kv_cache` in append - Githubissues

flashinfer-ai / flashinfer

FlashInfer: Kernel Library for LLM Serving

https://flashinfer.ai

Apache License 2.0

1.46k stars 143 forks source link

Fix the type of `paged_kv_cache` in append #597

Closed nandor closed 2 weeks ago

nandor commented 2 weeks ago

The type is adjusted to be consistent with the prefill/decode wrappers.