SOLVE_TRI extension to more dimensions (#17793)
* Extended TRI * Fix whitespace * chore: update webui build output * Just use cuBLAS for everything... * Merge both versions * Remove incorrect imports causing failures for CI * Still failing... remove all direct cublas imports and rely on common imports from "common.cuh" * Defines for hipBlas * Aaaand MUSA defines... * I hate this job... * Stupid typo... * Update ggml/src/ggml-cuda/solve_tri.cu Co-authored-by: Johannes Gäßler <johannesg@5d6.de> --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
parent
c6f6e4f96a
commit
53ecd4fdb9
6 changed files with 125 additions and 20 deletions
|
|
@ -7861,9 +7861,24 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
|
|||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 30, 30, 7, 1 }, { 8, 30, 7, 1 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 42, 42, 5, 2 }, { 10, 42, 5, 2 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 64, 64, 2, 2 }, { 10, 64, 2, 2 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 64, 64, 2, 2 }, { 64, 64, 2, 2 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 79, 79, 5, 3 }, { 417, 79, 5, 3 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 128, 128, 4, 2 }, { 32, 128, 4, 2 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 80, 80, 2, 8 }, { 80, 80, 2, 8 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 80, 80, 2, 8 }, { 79, 80, 2, 8 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 80, 80, 2, 8 }, { 81, 80, 2, 8 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 80, 80, 8, 8 }, { 80, 80, 8, 8 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 80, 80, 8, 8 }, { 79, 80, 8, 8 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 80, 80, 8, 8 }, { 81, 80, 8, 8 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 84, 84, 4, 4 }, { 32, 84, 4, 4 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 95, 95, 8, 8 }, { 40, 95, 8, 8 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 100, 100, 4, 4 }, { 41, 100, 4, 4 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 128, 128, 4, 4 }, { 31, 128, 4, 4 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 64, 64, 4, 4 }, { 300, 64, 4, 4 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 128, 128, 4, 4 }, { 32, 128, 4, 4 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 128, 128, 3, 4 }, { 32, 128, 3, 4 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 128, 128, 4, 1 }, { 32, 128, 4, 1 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 64, 64, 4, 4 }, { 200, 64, 4, 4 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 64, 64, 4, 4 }, { 384, 64, 4, 4 }));
|
||||
|
||||
for (bool v : {false, true}) {
|
||||
for (bool circular : {false, true}) {
|
||||
|
|
@ -8064,12 +8079,13 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
|
|||
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F16, GGML_TYPE_F32, 16416, 1, 128, {8, 1}, {4, 1}, {0, 2, 1, 3}));
|
||||
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F16, GGML_TYPE_F32, 128, 1, 16416, {8, 1}, {4, 1}, {0, 1, 2, 3}, 2*16416));
|
||||
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 64, 64, 4, 2 }, { 6, 64, 4, 2 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 128, 128, 4, 1 }, { 8, 128, 4, 1 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 64, 64, 4, 4 }, { 32, 64, 4, 4 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 128, 128, 4, 2 }, { 32, 128, 4, 2 }));
|
||||
// qwen3next with CHUNK_SIZE 64
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 64, 64, 8, 32 }, { 64, 64, 8, 32 }));
|
||||
// qwen3next with CHUNK_SIZE 128
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 128, 128, 4, 32 }, { 128, 128, 4, 32 }));
|
||||
test_cases.emplace_back(new test_solve_tri(GGML_TYPE_F32, { 256, 256, 4, 2 }, { 128, 256, 4, 2 }));
|
||||
|
||||
test_cases.emplace_back(new test_tri(GGML_TRI_TYPE_LOWER, GGML_TYPE_F32, { 256, 256, 4, 4 }));
|
||||
test_cases.emplace_back(new test_tri(GGML_TRI_TYPE_UPPER_DIAG, GGML_TYPE_F32, { 1024, 1024, 8, 4 }));
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue