mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-27 21:46:57 +02:00
Georgi Gerganov
bbdd9f246e
* 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
27 lines
921 B
Markdown
27 lines
921 B
Markdown
# 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.
|