test: refactor tests and fix inference edge cases

- Convert protocol and MoE test classes to plain functions
- Add real server/engine integration and generate_async tests
- Isolate test model per test and use pytest tmp_path
- Reset FastAPI engine state after inference tests
- Fix generate_async StopIteration handling on Python 3.12
- Fix HF adapter MoE dense/shared and Gemma qk_norm mapping
- Correct dev dependency httpx2 to httpx
This commit is contained in:
2026-08-21 22:59:51 +08:00
parent 7d27f3e078
commit dcc96de12a
11 changed files with 580 additions and 384 deletions
+2 -4
View File
@@ -31,13 +31,11 @@ def test_gradient_checkpointing_empty_modules_noop(test_model):
model = test_model["model"]
callback = GradientCheckpointingCallback()
originals = [layer.forward for layer in model.layers]
for layer in model.layers:
callback._enable(layer)
for layer, orig in zip(model.layers, originals):
assert layer.forward is orig
for layer in model.layers:
assert not hasattr(layer, "_original_forward")
def test_gradient_checkpointing_forward_unchanged(test_model):