ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-05 14:11:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

Revert "[CK_TILE] Add sequence padding and variable length support in fmha (a…" (#2883)

Browse Source 
This reverts commit 86dd59cd01.
This commit is contained in:
Illia Silin
2025-09-19 08:15:02 -07:00
committed by GitHub
parent 29446da1d5
commit b765fe78f3
13 changed files with 60 additions and 1032 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
example/ck_tile/01_fmha/example_fmha_fwd.cpp
View File

@@ -33,10 +33,6 @@ auto create_args(int argc, char* argv[])
"0",
"seqlen_k for new key/value, 0 means not to use this at all; "
"-1 to choose s_knew in [1, s] randomly.")
.insert("s_qpad",
"-1",
"seqlen_q stride between 2 batches (group-mode optional).\n"
"Provide positive strides per-batch to simulate physical padding on Q.")
.insert("s_kpad",
"-1",
"seqlen_k stride between 2 batches, currently used in group-mode only\n"
@@ -111,15 +107,7 @@ auto create_args(int argc, char* argv[])
.insert("warmup", "5", "number of iterations before benchmark the kernel")
.insert("repeat", "20", "number of iterations to benchmark the kernel")
.insert("json", "0", "0: No Json, 1: Dump Results in Json format")
.insert("jsonfile", "fmha_fwd.json", "json file name to dump results")
.insert("q_eff_lens",
"",
"Batch-mode only: per-batch effective seqlen for Q (exclude PAD).\n"
"Comma-separated list of length 'b'. If empty, no override.")
.insert("kv_eff_lens",
"",
"Batch-mode only: per-batch effective seqlen for KV (exclude PAD).\n"
"Comma-separated list of length 'b'. If empty, no override.");
.insert("jsonfile", "fmha_fwd.json", "json file name to dump results");
bool result = arg_parser.parse(argc, argv);
return std::make_tuple(result, arg_parser);
@@ -139,9 +127,6 @@ auto run(const ck_tile::ArgParser& arg_parser)
ck_tile::index_t hdim_v = arg_parser.get_int("d_v");
ck_tile::index_t seqlen_knew = arg_parser.get_int("s_knew");
auto seqlen_kpads = arg_parser.get_int_vec("s_kpad");
auto seqlen_qpads = arg_parser.get_int_vec("s_qpad");
auto q_eff_lens_per_batch = arg_parser.get_int_vec("q_eff_lens");
auto kv_eff_lens_per_batch = arg_parser.get_int_vec("kv_eff_lens");
ck_tile::index_t rotary_dim = arg_parser.get_int("rotary_dim");
bool i_perm = arg_parser.get_bool("iperm");
bool o_perm = arg_parser.get_bool("operm");
@@ -189,10 +174,7 @@ auto run(const ck_tile::ArgParser& arg_parser)
hdim_q,
hdim_v,
seqlen_knew,
seqlen_qpads,
seqlen_kpads,
q_eff_lens_per_batch,
kv_eff_lens_per_batch,
rotary_dim,
i_perm,
o_perm,