Files
ds4/docs/TESTING.md
T
Salvatore Sanfilippo 2f0bc1e3bf Split README into platform setup and focused reference guides
Keep the introduction and everyday usage in the README, with setup guides near the top and detailed references at the end. Document Ada/L40S support explicitly and replace stale model, memory, caching and performance claims.

Retain the root Strix Halo page as a link to its new guide.
2026-09-05 14:29:52 +02:00

2.5 KiB

Testing and Development

README

Read CONTRIBUTING.md before proposing an inference change. The release QA guide defines the hardware matrix, checkpoint-matched quality tests, long-context agent tasks, and speed checks. It also records which checks were not completed. A smoke test is not full QA.

Focused checks

Model-free checks include:

make ds4_test ds4_agent_test test-session-state
./ds4_test --server
./ds4_agent_test

On Metal, small GPU tensor tests are available without loading a full GGUF:

make tests/test_session_state_gpu tests/test_glm53_kda tests/test_mxfp4_metal
./tests/test_session_state_gpu
./tests/test_glm53_kda
./tests/test_mxfp4_metal

make test also includes model-backed tests. Select the right GGUF and ensure that it fits before running it; do not accidentally load a large model on a single device during multi-GPU QA. ROCm has make test-rocm.

Official-vector tests must use continuations from the same checkpoint as the GGUF. Flash 0731 and Vision Experimental are not interchangeable fixtures. See test vectors and quality scoring.

Investigating output

./ds4 --dump-tokens -p "..."
./ds4 --dump-logprobs /tmp/out.json --logprobs-top-k 20 --temp 0 -p "..."
./ds4 --dump-logits /tmp/logits.json --nothink --prompt-file prompt.txt
./ds4-server --trace /tmp/ds4-trace.txt

Token dumps catch template differences without inference. Logits and continuations help distinguish sampling changes from graph errors. Server traces include cache and tool-parser decisions. Keep traces private when they contain real conversations.

Tools and source references

For changes to state handling, cover rewind/replay, save/load, images, and multiple sessions as well as a fresh prompt. For distributed changes, exercise both ranks and failures; a local command-parser test is not physical TP QA.