LLM inference in C/C++
C++ ggml
tests : update Metal fusion baseline for beam (#30764)
Georgi Gerganov27af58168afd
diff --git a/skills/update-fusion-table/SKILL.md b/skills/update-fusion-table/SKILL.mdnew file mode 100644index 0000000000..4d545418db--- /dev/null+++ b/skills/update-fusion-table/SKILL.md@@ -0,0 +1,39 @@+---+name: update-fusion-table+description: Regenerate a per-device test-fusion baseline (tests/fusion/MTL.csv, ...) after fusion patterns or the dummy-model set change. Use when test-fusion --check fails.+---++# Update a fusion baseline++`tests/fusion/<BACKEND>.csv` is the `test-fusion` golden baseline: `arch,moe,mode,label,count`,+where `count` is how many times a fusion label matched per graph run. See `tests/fusion/README.md`.++Re-record only when the counts moved for the reason the contributor intended. A row failing on+`nmse_fus` (> 1e-4) is a fused-vs-unfused correctness bug, not baseline drift - fix it, never+record it away.++## Steps++```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 # always regenerate+./build/bin/test-llama-archs -o build-ci-models++D=MTL0; B=tests/fusion/MTL.csv; T=/tmp/$(basename $B) # keep the target backend/device in sync+./build/bin/test-fusion --models build-ci-models --device $D --check $B # read the FAIL rows+./build/bin/test-fusion --models build-ci-models --device $D --record $T+diff $B $T+cp $T $B+./build/bin/test-fusion --models build-ci-models --device $D --check $B # 0 failed, exit 0+```++- Read the diff before applying it. Every added, removed or changed row must be explainable by the+ change under review; an unexplained row means the run picked up something unintended.+- `expected 0` in a FAIL row = no baseline row for that label (new arch, or a fusion newly+ firing); non-zero `expected` = count changed; `fusion ... is no longer matched` = row stopped+ firing.+- `--record` rewrites the whole file, so never record a partial run (`--model FILE`, a filtered+ models dir) - it drops the rows of every architecture that was not run.+- `--record` marks every row `ok`; only the `--check` run validates.diff --git a/tests/fusion/MTL.csv b/tests/fusion/MTL.csvindex 9ab1f1f3f8..e6cd43a82b 100644--- a/tests/fusion/MTL.csv+++ b/tests/fusion/MTL.csv@@ -20,6 +20,8 @@ bailingmoe3 ,1 ,any ,GATED_DELTA_NET+CPY , 1bailingmoe3 ,1 ,any ,MUL+ADD , 2bailingmoe3 ,1 ,any ,RMS_NORM+MUL , 8bailingmoe3 ,1 ,any ,RMS_NORM+SCALE , 2+beam ,0 ,any ,MUL+ADD , 6+beam ,0 ,any ,RMS_NORM+MUL , 25bloom ,0 ,any ,NORM+MUL+ADD , 6chatglm ,0 ,any ,RMS_NORM+MUL , 5codeshell ,0 ,any ,NORM+MUL+ADD , 5