Hi,
Thanks for the great framework! I am trying to compile and run the benchmark. However, I meet some problems when I compile decode kernel tests/benchmarks. After I run make -j12, I met this error if set(FLASHINFER_DECODE ON):
[ 98%] Building CUDA object CMakeFiles/bench_batch_decode.dir/src/bench_batch_decode.cu.o
/home/admin/llm-acceleration/flashinfer/src/bench_batch_decode.cu(156): error: no instance of function template "flashinfer::BatchPrefillWithPagedKVCacheWrapper" matches the argument list
argument types are: (flashinfer::BatchPrefillHandler *, half *, int32_t *, std::nullptr_t, flashinfer::paged_kv_t<flashinfer::PageStorage::kIndices, flashinfer::QKVLayout::kNHD, half, int32_t>, half *, std::nullptr_t, size_t, __nv_bool, const flashinfer::RotaryMode)
cudaError_t status = BatchPrefillWithPagedKVCacheWrapper<PageStorage::kIndices, kv_layout, T, T, int32_t>(
^
detected during instantiation of "void bench_flashinfer_batch_decode_with_prefill(nvbench::state &) [with T=half]"
1 error detected in the compilation of "/home/admin/llm-acceleration/flashinfer/src/bench_batch_decode.cu".
make[2]: *** [CMakeFiles/bench_batch_decode.dir/build.make:76: CMakeFiles/bench_batch_decode.dir/src/bench_batch_decode.cu.o] Error 1
make[1]: *** [CMakeFiles/Makefile2:279: CMakeFiles/bench_batch_decode.dir/all] Error 2
make: *** [Makefile:136: all] Error 2
What can I do to figure it out? Thank you!