LLM inference in C/C++
C++ ggml
tests : add fusion baseline README and broaden fusion CI triggers (#28893)
Georgi Gerganovbbdd9f246e96
diff --git a/.github/workflows/fusion.yml b/.github/workflows/fusion.ymlindex ad7d5ab60e..7c8596467a 100644--- a/.github/workflows/fusion.yml+++ b/.github/workflows/fusion.yml@@ -9,7 +9,9 @@ on:'.github/workflows/fusion.yml','ggml/**','tests/fusion/**',- 'tests/test-fusion.cpp'+ 'tests/test-fusion.cpp',+ 'tests/test-llama-archs.cpp',+ 'src/models/**']pull_request:@@ -18,7 +20,9 @@ on:'.github/workflows/fusion.yml','ggml/**','tests/fusion/**',- 'tests/test-fusion.cpp'+ 'tests/test-fusion.cpp',+ 'tests/test-llama-archs.cpp',+ 'src/models/**']concurrency:diff --git a/.pi/gg/SYSTEM.md b/.pi/gg/SYSTEM.mdindex 369b87bcd5..bd308ea963 100644--- a/.pi/gg/SYSTEM.md+++ b/.pi/gg/SYSTEM.md@@ -23,6 +23,7 @@ Pull requests (PRs):- For the AI usage disclosure section, write "YES. pi:llama.cpp/[MODEL]"- If `PI_MODEL_NAME` env var is not set, ask the user to tell you what model was used and write it in place of [MODEL]- Always create the pull requests in draft mode+- Never reply to review comments or post comments on issues/PRs without explicit permission from the userCommits:- On every commit that you make, include a "Assisted-by: pi:llama.cpp/[MODEL]" tagdiff --git a/tests/fusion/README.md b/tests/fusion/README.mdnew file mode 100644index 0000000000..3ac02b061e--- /dev/null+++ b/tests/fusion/README.md@@ -0,0 +1,26 @@+# Fusion baselines++Per-device baselines for `test-fusion`, one CSV per backend (e.g. `MTL.csv`). Rows are+`arch,moe,mode,label,count`. Regenerate a CSV whenever fusion patterns change.++## Update a baseline++```sh+cmake -B build -DCMAKE_BUILD_TYPE=Release -DGGML_METAL=ON # enable the target backend+cmake --build build --config Release --target test-llama-archs --target test-fusion -j++rm -rf build-ci-models && mkdir -p build-ci-models+./build/bin/test-llama-archs -o build-ci-models++./build/bin/test-fusion --models build-ci-models --device MTL0 --record MTL.csv+```++## Validate++```sh+./build/bin/test-fusion --models build-ci-models --device MTL0 --check MTL.csv+```++Non-zero exit means a row differs from the baseline. Use `--model FILE` to run a single+architecture. Note `--check` only sees present rows — a fusion that stops matching is not+reported, so diff the recorded CSV to catch removed patterns.