flashinfer-ai / flashinfer

FlashInfer: Kernel Library for LLM Serving
https://flashinfer.ai
Apache License 2.0
1.48k stars 147 forks source link

test: add DtypeKV template param in bench_batch_decode #607

Closed dc3671 closed 2 weeks ago

dc3671 commented 2 weeks ago

Add typename TKV so that it's convenient to benchmark FP8 KVCache. A example output: image