Skip to content

[https://nvbugs/6462303][fix] Import MpiPoolSession under a second private alias (_RealMpiPoolSession)… #16497

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
trtllm-agent wants to merge 1 commit into from
+8 −4
Closed

[https://nvbugs/6462303][fix] Import MpiPoolSession under a second private alias (_RealMpiPoolSession)… #16497

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 8 additions & 3 deletions tensorrt_llm/executor/proxy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,8 +28,12 @@
from tensorrt_llm.logger import logger

from .._utils import customized_gc_thresholds, mpi_rank, nvtx_range_debug
from ..llmapi.mpi_session import (MpiCommSession, MpiPoolSession, MpiSession,
RemoteMpiCommSessionClient,
# Alias unaffected by test-infra monkey-patching of ``MpiPoolSession`` (which
# replaces the module-level name with a factory function for pool reuse).
from ..llmapi.mpi_session import MpiCommSession
from ..llmapi.mpi_session import MpiPoolSession
from ..llmapi.mpi_session import MpiPoolSession as _RealMpiPoolSession
from ..llmapi.mpi_session import (MpiSession, RemoteMpiCommSessionClient,
validate_session_world_size)
from ..llmapi.tracer import enable_llm_tracer, get_tracer, global_tracer
from ..llmapi.utils import (AsyncQueue, ManagedThread, _SyncQueue,
Expand Down Expand Up @@ -573,7 +577,8 @@ def mpi_done_callback(future: concurrent.futures.Future):
raise RuntimeError(
"Executor worker returned error") from ready_signal

if isinstance(self.mpi_session, MpiPoolSession) and len(status) == 3:
if isinstance(self.mpi_session,
_RealMpiPoolSession) and len(status) == 3:
worker_process_identities: List[WorkerProcessIdentity] = status[2]
self._worker_process_monitor.register(worker_process_identities)

Expand Down
1 change: 0 additions & 1 deletion tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -376,7 +376,6 @@ full:RTX_PRO_6000_Blackwell_Server_Edition/perf/test_perf.py::test_perf[quant:w4
full:sm100/examples/test_nemotron.py::test_llm_nemotron_3_8b_1gpu[bfloat16-fp8] SKIP (megatron-core 0.8 is not supported in python 3.12)
full:sm100/unittest/bindings SKIP (Disable for Blackwell)
kv_cache/test_kv_cache_v2_scheduler.py::TestKVCacheV2Llama::test_chunked_prefill SKIP (https://nvbugs/6428002)
kv_cache/test_kv_cache_v2_scheduler.py::TestKVCacheV2Llama::test_eviction_with_block_reuse SKIP (https://nvbugs/6462303)
llmapi/test_llm_api_pytorch_bart.py::test_bart_pytorch_generate_encoder_decoder_end_to_end[bf16-kv-v1-cuda-graph-on-greedy-tp2-bart-large-cnn] SKIP (https://nvbugs/6463812)
llmapi/test_llm_api_pytorch_moe_lora.py::test_mixtral_moe_routed_expert_fp8_multi_lora_varying_ranks[cudagraph] SKIP (https://nvbugs/6463829)
llmapi/test_llm_api_pytorch_moe_lora.py::test_mixtral_moe_routed_expert_fp8_multi_lora_varying_ranks[eager] SKIP (https://nvbugs/6463829)
Expand Down
Loading