mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-04 18:21:52 +08:00
[https://nvbugs/5612438][fix] Add timeout for SeedOSS test (#8683)
Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com>
This commit is contained in:
parent
5553391c5e
commit
ca9f70f78c
@ -5324,6 +5324,7 @@ class TestSeedOss_36B(LlmapiAccuracyTestHarness):
|
||||
max_tokens=16384)
|
||||
|
||||
@skip_pre_hopper
|
||||
@pytest.mark.timeout(7200)
|
||||
@pytest.mark.skip_less_device_memory(140000)
|
||||
def test_auto_dtype(self):
|
||||
kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.8)
|
||||
|
||||
@ -203,7 +203,6 @@ accuracy/test_llm_api_pytorch.py::TestNemotronNas::test_auto_dtype_tp8 SKIP (htt
|
||||
unittest/_torch/auto_deploy/unit/multigpu/test_ad_build_small_multi.py::test_build_ad[meta-llama/Meta-Llama-3.1-8B-Instruct-llm_extra_args0-2] SKIP (https://nvbugs/5680755)
|
||||
full:H100_PCIe/unittest/llmapi/test_llm_pytorch.py::test_llama_7b_multi_lora_evict_and_reload_lora_gpu_cache SKIP (https://nvbugs/5682551)
|
||||
unittest/_torch/speculative/test_draft_len_schedule.py::test_correctness_across_batch_sizes[model_drafter-schedule1] SKIP (https://nvbugs/5680911)
|
||||
accuracy/test_llm_api_pytorch.py::TestSeedOss_36B::test_auto_dtype SKIP (https://nvbugs/5612438)
|
||||
test_e2e.py::test_openai_completions_example[trt] SKIP (https://nvbugs/5701450)
|
||||
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[tp4-fp8kv=False-attn_backend=TRTLLM-torch_compile=False] SKIP (https://nvbugs/5701457)
|
||||
triton_server/test_triton_llm.py::test_llmapi_backend[4-0-disableDecoupleMode-tensorrt_llm] SKIP (https://nvbugs/5701480)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user