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/5760737][test] only skip mooncake+indexerkcache test (#10266)

Browse Source 
Signed-off-by: zhengd-nv <200704041+zhengd-nv@users.noreply.github.com>
This commit is contained in:
Zheng Duan 2026-01-21 09:48:39 +08:00 committed by GitHub
parent 3c8ed19440
commit 26c23cf99f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
cpp/tensorrt_llm/executor/cache_transmission/mooncake_utils/transferAgent.cpp
View File

@ -98,13 +98,14 @@ TransferState MooncakeTransferStatus::wait(int64_t timeout_ms) const
mBatchFreed = true;
TLLM_LOG_DEBUG("Batch ID %lu freed in wait()", mBatchId);
syncSegmentCache(mEngine);
std::this_thread::sleep_for(std::chrono::milliseconds(1));
return TransferState::kSUCCESS;
}
// If timeout_ms < 0, wait indefinitely
if (timeout_ms < 0)
{
std::this_thread::yield();
std::this_thread::sleep_for(std::chrono::milliseconds(1));
continue;
}
@ -117,7 +118,7 @@ TransferState MooncakeTransferStatus::wait(int64_t timeout_ms) const
return TransferState::kIN_PROGRESS;
}
std::this_thread::yield();
std::this_thread::sleep_for(std::chrono::milliseconds(1));
}
}

5
cpp/tests/unit_tests/multi_gpu/cacheTransceiverTest.cpp
View File

@ -1304,6 +1304,11 @@ TEST_P(AsymmetricalCacheTest, TestCase)
{
GTEST_SKIP() << "Temporarily skipping cache transceiver tests with NIXL and MOONCAKE backend for CP.";
}
if (isIndexerKCache && tensorrt_llm::common::getEnvUseMooncakeKvCache())
{
// https://nvbugs/5760737
GTEST_SKIP() << "Temporarily skipping cache transceiver tests with Mooncake backend for Indexer KCache.";
}
std::vector<int> lenList = {30, 10, 60, 80};
if (genCp > 1)
{

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

@ -252,7 +252,6 @@ examples/test_granite.py::test_llm_granite[granite-3.0-1b-a400m-instruct-bfloat1
examples/test_granite.py::test_llm_granite[granite-3.0-2b-instruct-bfloat16] SKIP (https://nvbugs/5608979)
unittest/executor/test_base_worker.py::TestWorkerBase SKIP (https://nvbugs/5759698)
triton_server/test_triton.py::test_gpt_disaggregated_serving_bls[gpt-disaggregated-serving-bls] SKIP (https://nvbugs/5582118)
cpp/test_multi_gpu.py::test_cache_transceiver[8proc-mooncake_kvcache-90] SKIP (https://nvbugs/5760737)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[trtllm-two_model-no_overlap_scheduler] SKIP (https://nvbugs/5760747)
unittest/_torch/multi_gpu/test_mnnvl_allreduce.py::test_row_linear_residual_norm_fusion[no_fusion-strategy:8-dtype:bfloat16-hidden:8192-seqlen:[15]] SKIP (https://nvbugs/5761364)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False-enable_chunked_prefill=False] SKIP (https://nvbugs/5759338)