kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[https://nvbugs/5448579][fix] EXAONE-4.0 accuracy test bugfix (#6888)

Browse Source 
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
This commit is contained in:
Yechan Kim 2025-08-19 16:29:32 +09:00 committed by GitHub
parent d4dd5b4f4d
commit d6c2a6a81f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/integration/defs/accuracy/test_llm_api_pytorch.py
View File

@ -2373,10 +2373,8 @@ class TestPhi4MM(LlmapiAccuracyTestHarness):
class TestEXAONE4(LlmapiAccuracyTestHarness):
MODEL_NAME = "LGAI-EXAONE/EXAONE-4.0-32B"
kv_cache_config = KvCacheConfig(
enable_block_reuse=False,
enable_partial_reuse=False,
max_attention_window=[4096, 4096, 4096, 131072])
kv_cache_config = KvCacheConfig(enable_block_reuse=False,
enable_partial_reuse=False)
def test_auto_dtype(self):
model_path = f"{llm_models_root()}/EXAONE-4.0-32B"