[CI] green llama tests (#37244)

* green llama tests

* use cleanup instead

* better test comment; cleanup upgrade

* better test comment; cleanup upgrade
This commit is contained in:
Joao Gante
2025-04-03 14:15:53 +01:00
committed by GitHub
parent 782d7d945d
commit 9a1c1fe7ed
15 changed files with 62 additions and 36 deletions

View File

@@ -226,7 +226,7 @@ class AqlmTest(unittest.TestCase):
# Setup static KV cache for generation
past_key_values = StaticCache(
config=self.quantized_model.config,
batch_size=1,
max_batch_size=1,
max_cache_len=seq_length + self.max_new_tokens + 1,
device=torch_device,
dtype=self.quantized_model.config._pre_quantization_dtype,