kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-05 18:51:38 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[https://nvbugs/5814253][fix] unwaive test_autotuner_distributed_strategy tests (#10793)

Browse Source 
Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>
This commit is contained in:
Yukun He 2026-01-21 15:37:11 +08:00 committed by GitHub
parent 1592dfab6d
commit a4152c80f6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tensorrt_llm/_torch/autotuner.py
View File

@ -505,9 +505,8 @@ class AutoTunerProfilingCache:
fcntl.flock(f, fcntl.LOCK_SH)
current_cache_contents = json.load(f)
self._deserialize_metadata(current_cache_contents["metadata"])
assert f"rank_{rank}" in current_cache_contents, f"Rank {rank} cache not found in {file_path}"
self.cache = self._deserialize_cache_data(
current_cache_contents[f'rank_{rank}'])
current_cache_contents.get(f'rank_{rank}', {}))
logger.info(
f"[AutoTuner] Successfully loaded cache from {file_path} using JSON format"
)

1
tests/integration/test_lists/waives.txt
View File

@ -356,7 +356,6 @@ accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_auto_dtype_4gpus[4-4
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency] SKIP (https://nvbugs/5814309)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[tp4-mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/5800646)
unittest/_torch/thop/parallel/test_fp4_swizzle.py::test_swizzle_sf SKIP (https://nvbugs/5811159)
unittest/_torch/misc/test_autotuner.py::test_autotuner_distributed_strategy[2-DistributedTuningStrategy.BROADCAST] SKIP (https://nvbugs/5814253)
stress_test/stress_test.py::test_run_stress_test[llama-v3-8b-instruct-hf_tp1-stress_time_300s_timeout_450s-MAX_UTILIZATION-pytorch-stress-test] SKIP (https://nvbugs/5814203)
unittest/_torch/attention/test_trtllm_flashinfer_symbol_collision.py::test_flashinfer_fused_moe_matches_torch_moe SKIP (https://nvbugs/5814215)
full:sm89/accuracy/test_llm_api_pytorch.py::TestNemotronV3Nano::test_auto_dtype SKIP (https://nvbugs/5814504)