mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
b79e0435de
# What does this PR do? we randomly get errors like the following, it's most likely due to accessing an object that is already deallocated ``` E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] Traceback (most recent call last): E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 90, in _wrap E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] fn(i, *args) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 611, in _wrap E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] ret = record(fn)(*args_) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] return f(*args, **kwargs) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/internal-llama-stack/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py", line 249, in worker_process_entrypoint E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] task = req_gen.send(result) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/internal-llama-stack/llama_stack/providers/inline/inference/meta_reference/parallel_utils.py", line 156, in retrieve_requests E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] torch.distributed.broadcast_object_list( E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/distributed/c10d_logger.py", line 81, in wrapper E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] return func(*args, **kwargs) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/distributed/distributed_c10d.py", line 3504, in broadcast_object_list E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] object_list[i] = _tensor_to_object(obj_view, obj_size, group) E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] File "/home/yyy/.conda/envs/myenv/lib/python3.10/site-packages/torch/distributed/distributed_c10d.py", line 2961, in _tensor_to_object E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] return _unpickler(io.BytesIO(buf)).load() E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] EOFError: Ran out of input E0318 12:55:24.472000 1562188 site-packages/torch/distributed/elastic/multiprocessing/api.py:732] Process SpawnProcess-1: Traceback (most recent call last): ``` ## Test Plan start server ``` llama-stack-client eval run-benchmark mmmu_v1 --model-id meta-llama/Llama-4-17B-Omni-Instruct --output-dir /tmp/mmmu_standard --num-examples 30 ``` [//]: # (## Documentation) |
||
|---|---|---|
| .. | ||
| llama3 | ||
| quantization | ||
| __init__.py | ||
| common.py | ||
| config.py | ||
| inference.py | ||
| model_parallel.py | ||
| parallel_utils.py | ||