tests : add fusion baseline README and broaden fusion CI triggers (#28893)

* tests : add README for updating the per-backend fusion baselines

Assisted-by: pi:llama.cpp/Qwen3.8-27B

* ci : trigger fusion on changes to test-llama-archs.cpp and src/models

the dummy models and their architectures drive the fusion baselines, so a
change to either can alter the per-fusion counters and should re-run the
fusion job.

Assisted-by: pi:llama.cpp/Qwen3.8-27B

* tests : merge the fusion build commands in the README

assisted-by: pi:llama.cpp/Qwen3.8-27B

* pi : require explicit permission before posting PR/issue comments

assisted-by: pi:llama.cpp/Qwen3.8-27B
This commit is contained in:
Georgi Gerganov
2026-09-14 15:45:05 +03:00
committed by GitHub
parent 97e4ca7358
commit bbdd9f246e
3 changed files with 33 additions and 2 deletions
+6 -2
View File
@@ -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:
+1
View File
@@ -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 user
Commits:
- On every commit that you make, include a "Assisted-by: pi:llama.cpp/[MODEL]" tag
+26
View File
@@ -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.