tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-20 09:37:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda : support Falcon-H1 state size for SSM_SCAN (#14602)

Browse Source
This commit is contained in:
compilade
2025-07-09 23:54:38 -04:00
committed by GitHub
parent cb9178f885
commit a57d1bcb3c
3 changed files with 16 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/test-backend-ops.cpp
View File

@ -5069,6 +5069,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_ssm_scan(GGML_TYPE_F32, 16, 1, 1024, 1, 32, 4)); // Mamba-1
test_cases.emplace_back(new test_ssm_scan(GGML_TYPE_F32, 128, 64, 16, 2, 32, 4)); // Mamba-2
test_cases.emplace_back(new test_ssm_scan(GGML_TYPE_F32, 256, 64, 8, 2, 32, 4)); // Falcon-H1
test_cases.emplace_back(new test_rwkv_wkv6(GGML_TYPE_F32, 32, 64, 1, 1));
test_cases.emplace_back(new test_rwkv_wkv6(GGML_TYPE_F32, 32, 64, 32, 1));