Skip to content

[https://nvbugs/5680310][fix] Fix ctx only timed out test #9410

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

Merged
merged 2 commits into from
Nov 27, 2025
+4 −5
Merged

[https://nvbugs/5680310][fix] Fix ctx only timed out test #9410

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3a962f5
fix: Fix ctx timed out test by using UCX backend
pcastonguay Nov 21, 2025
eed02da
Removing test from waives
pcastonguay Nov 24, 2025
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
4 changes: 2 additions & 2 deletions cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -493,8 +493,8 @@ void CacheTransceiver::checkContextTransferStatus(std::optional<int> const& atLe
}
else if (status == std::future_status::timeout)
{
TLLM_LOG_WARNING("Timed out waiting for context transfer for request %ld after %d milliseconds.",
request->mRequestId, senderFutureTimeoutMs.value());
TLLM_LOG_WARNING("Timed out waiting for context KV cache transfer after %d milliseconds.",
senderFutureTimeoutMs.value());
++it;
}
else
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 @@ -409,7 +409,6 @@ accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp8_eagle3_tp8[
accuracy/test_llm_api_pytorch.py::TestNemotronNas::test_auto_dtype_tp8 SKIP (https://nvbugs/5673527)
disaggregated/test_auto_scaling.py::test_disagg_server_restart[etcd-round_robin] SKIP (https://nvbugs/5633340)
disaggregated/test_auto_scaling.py::test_disagg_server_restart[http-round_robin] SKIP (https://nvbugs/5633340)
unittest/llmapi/test_llm_pytorch.py::test_llm_context_only_timed_out_kv_cache_exhausted SKIP (https://nvbugs/5680310)
accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[False-4] SKIP (https://nvbugs/5680312, https://nvbugs/5636912)
accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[False-2] SKIP (https://nvbugs/5680312, https://nvbugs/5636912)
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)
Expand Down
4 changes: 2 additions & 2 deletions tests/unittest/llmapi/test_llm_pytorch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -986,7 +986,7 @@ def test_llm_context_only_timed_out():
kv_cache_config=global_kvcache_config,
tensor_parallel_size=tp_size,
cache_transceiver_config=CacheTransceiverConfig(
backend="DEFAULT", kv_transfer_timeout_ms=1000),
backend="UCX", kv_transfer_timeout_ms=1000),
**llm_args_extra)

max_tokens = 1
Expand Down Expand Up @@ -1064,7 +1064,7 @@ def test_llm_context_only_timed_out_kv_cache_exhausted(
kv_cache_config=kv_cache_config,
tensor_parallel_size=tp_size,
cache_transceiver_config=CacheTransceiverConfig(
backend="DEFAULT",
backend="UCX",
kv_transfer_timeout_ms=1000,
kv_transfer_sender_future_timeout_ms=sender_future_timeout_ms),
**llm_args_extra)
Expand Down
Loading