vulkan: sparse flash attention for quantized K/V (#29639)
* vulkan: sparse flash attention for quantized K/V Assisted-by: Claude * vulkan: single-scan sparse FA index compaction The compaction ran one workgroup per mask row and walked the row in BLOCK_SIZE chunks, with a workgroup scan per chunk. For decode that is one workgroup doing KV/1024 barrier-bound iterations, so at 128k cells it cost more than the sparse attention it feeds. Split the row into contiguous segments instead: one per subgroup with ballot counting over coalesced loads, or one per thread without subgroups. A single scan over the segment counts then gives each segment its output offset. The index list stays ascending.
This commit is contained in:
1 parent
c173a53bdf
commit
b3daa077a5
4 files changed
+93
-55
No files matched your search
@@ -11359,6 +11359,14 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
|
||||
|
||||
// Qwen QSA: 256/256, gqa 12, budget 2048.
|
||||
test_cases.emplace_back(new test_flash_attn_ext(256, 256, 2, {12, 1}, 8192, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16, GGML_TYPE_F16, {0, 1, 2, 3}, true, false, 2048));
|
||||
// quantized cache, deep enough to take the sparse path
|
||||
test_cases.emplace_back(new test_flash_attn_ext(256, 256, 2, {12, 1}, 32768, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0, {0, 1, 2, 3}, true, false, 2048));
|
||||
test_cases.emplace_back(new test_flash_attn_ext(256, 256, 2, {12, 1}, 32768, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0, {0, 1, 2, 3}, true, false, 2048));
|
||||
// single head with quantized K (MMQ on Vulkan)
|
||||
test_cases.emplace_back(new test_flash_attn_ext(128, 128, 1, { 1, 1}, 8192, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0, {0, 1, 2, 3}, true, false, 512));
|
||||
test_cases.emplace_back(new test_flash_attn_ext(128, 128, 1, { 1, 1}, 8192, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q4_1, GGML_TYPE_Q4_1, {0, 1, 2, 3}, true, false, 512));
|
||||
// KV not a multiple of the compaction workgroup size.
|
||||
test_cases.emplace_back(new test_flash_attn_ext(128, 128, 1, { 8, 1}, 5003, 4, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16, GGML_TYPE_F16, {0, 1, 2, 3}, true, false, 512));
|
||||
|
||||
// more V-is-sub-view-of-K cases: other head shapes, and full views with equal head sizes
|
||||
test_cases.emplace_back(new test_flash_attn_ext(320, 256, 1, {32, 1}, 512, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16, GGML_TYPE_F16, {0, 1, 2, 3}, true, true));
|
||||
@@ -11830,6 +11838,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
|
||||
test_cases.emplace_back(new test_flash_attn_ext(512, 512, 1, { 8, 1}, kv, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16, GGML_TYPE_F16, {0, 1, 2, 3}, true, false, 512));
|
||||
test_cases.emplace_back(new test_flash_attn_ext(576, 512, 1, {16, 1}, kv, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16, GGML_TYPE_F16, {0, 1, 2, 3}, true, true, 512));
|
||||
test_cases.emplace_back(new test_flash_attn_ext(256, 256, 2, {12, 1}, kv, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16, GGML_TYPE_F16, {0, 1, 2, 3}, true, false, 2048));
|
||||
test_cases.emplace_back(new test_flash_attn_ext(256, 256, 2, {12, 1}, kv, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0, {0, 1, 2, 3}, true, false, 2048));
|
||||
test_cases.emplace_back(new test_flash_attn_ext(256, 256, 2, {12, 1}, kv, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0, {0, 1, 2, 3}, true, false, 0));
|
||||
}
|
||||
|
||||
test_cases.emplace_back(new test_flash_attn_ext(64, 64, 8, {8, 1}, 7680, 1, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16, GGML_TYPE_F16));
|
||||
|
||||
Reference in new issue
Block a user