Skip to content

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

C++

ple_residency_test is registered with the GPU-build tests (it sat in the conversation-tests block, which is off by default, so ctest never ran it)

Niko12213e2f45e2e12c
diff --git a/CMakeLists.txt b/CMakeLists.txt
index d67949f28..49aa21807 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -138,9 +138,6 @@ if(STRATA_BUILD_CONVERSATION_TESTS)
add_executable(conversation_memory_test src/core/conversation_memory_test.cpp src/core/conversation_memory.cpp)
target_include_directories(conversation_memory_test PRIVATE include)
add_test(NAME conversation_memory_test COMMAND conversation_memory_test)
- add_executable(ple_residency_test src/core/ple_residency_test.cpp)
- target_include_directories(ple_residency_test PRIVATE include)
- add_test(NAME ple_residency_test COMMAND ple_residency_test)
add_executable(conversation_file_test src/core/conversation_file_test.cpp src/core/conversation_file.cpp)
target_include_directories(conversation_file_test PRIVATE include)
add_test(NAME conversation_file_test COMMAND conversation_file_test)
@@ -1490,6 +1487,11 @@ if(STRATA_ENABLE_CUDA OR STRATA_ENABLE_HIP)
target_link_libraries(ple_reader_test PRIVATE strata_kernels ${_strata_gpu_runtime_target})
add_test(NAME ple_reader_selftest COMMAND ple_reader_test --selftest)
+ # 0.2.7: the PLE residency rule (table + expert arena + headroom); header-only, needs nothing
+ add_executable(ple_residency_test src/core/ple_residency_test.cpp)
+ target_include_directories(ple_residency_test PRIVATE include)
+ add_test(NAME ple_residency_test COMMAND ple_residency_test)
+
# The GPU test runs ON THE TARGET PC. `--selftest` allocates
# and writes real VRAM, so a machine without a device fails this test rather than skipping it silently -
# which is correct: an engine that targets one GPU should not report a pass for having no GPU.