tests : add test-model-random

This generates random models and then tests different concurrencies
of batches to check if the output is consistent.

This can detect when e.g. the recurrent cache has been broken,
or anything else which would affect the consistency of the output
when inferencing multiple distinct sequences.

More architectures will be added, but for now this starts with Mamba.

Eventually, consistency of pooled embeddings will also be tested.

The goal is to reduce accidental regressions
by making it easy to quickly test a lot of edge cases
on the supported architectures,
without having to download any model.

Author: compilade

tests/CMakeLists.txt

@@ -193,6 +193,7 @@ endif()
 # llama_build_and_test(test-opt.cpp) # SLOW
 llama_build_and_test(test-gguf.cpp)
 llama_build_and_test(test-backend-ops.cpp)
+llama_build_and_test(test-model-random.cpp)
 
 llama_build_and_test(test-model-load-cancel.cpp  LABEL "model")
 llama_build_and_test(test-autorelease.cpp        LABEL "model")