CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-19 11:57:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

tests : add test-model-random

Browse Source 
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.
This commit is contained in:
Francis Couture-Harpin
2025-06-11 17:53:55 -04:00
parent 2e89f76b7a
commit 9cd402cbe1
2 changed files with 921 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/CMakeLists.txt
View File

@@ -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")