[CK_TILE] FMHA Reduce build time by disabling instances that are not tested (#2834)

* Use lse = false for PagedKV tests

There are no instances with lse = true so splitkv is actually launched
as a fallback.

* Reduce build time by disabling instances that are not tested

[ROCm/composable_kernel commit: 847834a408]

example/ck_tile/01_fmha/CMakeLists.txt

@@ -26,7 +26,7 @@ endforeach()
 
 # "fwd" is a must-have api for the fmha_fwd example, add it if not specified
 if(NOT "fwd" IN_LIST FMHA_FWD_ENABLE_APIS)
-  list(APPEND FMHA_FWD_ENABLE_APIS "fwd")
+  list(PREPEND FMHA_FWD_ENABLE_APIS "fwd")
 endif()
 
 file(GLOB_RECURSE CODE_GEN_SCRIPTS CONFIGURE_DEPENDS
@@ -51,6 +51,15 @@ set(FMHA_BWD_CODE_GEN_COMMON_ARGS
   # --filter fmha_bwd_dot...@fmha_bwd_convert...@fmha_bwd...
 )
 
+# Reduce building time by disabling instances that are not currently used in the gtests
+# TODO: Consider to use a special receipt for testing only, or even two receipts: a small subset of
+# instances for quick CI runs and a larger subset for scheduled runs (the tests skip tests when
+# there is no corresponding instance for parameters).
+if(BUILD_TESTING)
+  # Filters are in the order of FMHA_FWD_KNOWN_APIS: fwd,fwd_splitkv_combine@fwd_splitkv,fwd_appendkv,pagedkv_prefill
+  list(APPEND FMHA_FWD_CODE_GEN_COMMON_ARGS --filter *_nlogits*_nskip*,*@*_nlogits*_nbias*,*,*_nlogits*_nskip*_pagedkv)
+endif()
+
 # generate a list of kernels, but not actually emit files at config sta
 execute_process(
   COMMAND ${Python3_EXECUTABLE} ${FMHA_FWD_CODE_GEN_COMMON_ARGS}

test/ck_tile/fmha/test_fmha_fwd.inc

@@ -401,7 +401,7 @@ TEST_P(PagedKV, Test)
                                                0,               // scale_s
                                                0,               // logits_soft_cap
                                                is_v_rowmajor,   // is_v_rowmajor
-                                               def_lse,         // lse
+                                               false,           // lse
                                                page_block_size, // page_block_size
                                                false,           // use_cache_batch_idx
                                                "n",             // bias_str