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/5532023][fix] unwaive GenerationExecutor tests (#8251)

Browse Source 
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>
This commit is contained in:
Yan Chunwei 2025-10-11 10:43:04 +08:00 committed by Yanchao Lu
parent 179c7dc501
commit 4e51148088
1 changed files with 0 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/unittest/llmapi/test_llm_multi_gpu.py
View File

@ -75,7 +75,6 @@ def engine_from_checkpoint() -> tempfile.TemporaryDirectory:
return tmpdir
@pytest.mark.skip(reason="https://nvbugs/5532023")
@pytest.mark.gpu2
@pytest.mark.part0
def test_llm_loading_from_ckpt_for_tp2(
@ -98,7 +97,6 @@ def test_llm_generate_tp2():
kv_cache_config=global_kv_cache_config)
@pytest.mark.skip(reason="https://nvbugs/5532023")
def test_llm_explicit_shutdown():
# with-statement will invoke `shutdown()` explicitly
with LLM(model=llama_model_path,
@ -137,7 +135,6 @@ def test_llm_return_logprobs_tp2(prompt_logprobs: Optional[int],
tp_size=2)
@pytest.mark.skip(reason="https://nvbugs/5532023")
@pytest.mark.parametrize("use_auto_parallel", [True, False],
ids=["enable_auto_parallel", "disable_auto_parallel"])
@pytest.mark.parametrize("from_ckpt", [True, False],
@ -170,7 +167,6 @@ def test_llm_generate_mixtral_for_tp2():
print(output)
@pytest.mark.skip(reason="https://nvbugs/5532023")
@skip_gpu_memory_less_than(70 * 1024**3)
@pytest.mark.gpu2
@pytest.mark.part1
@ -316,7 +312,6 @@ def run_command(command: str):
raise e
@pytest.mark.skip(reason="https://nvbugs/5532023")
@skip_single_gpu
def test_llm_multi_node(engine_from_checkpoint: tempfile.TemporaryDirectory):
nworkers = 2
@ -521,7 +516,6 @@ def llm_for_sampling_params_tp2():
llm.shutdown()
@pytest.mark.skip(reason="https://nvbugs/5532023")
@pytest.mark.parametrize("sampling_params",
sampling_params_for_aborting_request)
def test_llm_abort_request_tp2(llm_for_sampling_params_tp2: LLM,