kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Fix: NVBug 5302895 (#4835)

Browse Source 
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
This commit is contained in:
Shi Xiaowei 2025-06-04 09:31:39 +08:00 committed by GitHub
parent c835f06371
commit b13f8c9cba
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tensorrt_llm/executor/serialization.py
View File

@ -63,7 +63,8 @@ BASE_ZMQ_CLASSES = {
"FinishReason", "KvCacheConfig", "KvCacheTransferMode",
"KvCacheRetentionConfig",
"KvCacheRetentionConfig.TokenRangeRetentionConfig", "PeftCacheConfig",
"SchedulerConfig", "DynamicBatchConfig"
"SchedulerConfig", "DynamicBatchConfig", "ContextChunkingPolicy",
"CacheTransceiverConfig"
],
"tensorrt_llm._torch.pyexecutor.config": ["PyTorchConfig"],
"tensorrt_llm._torch.model_config": ["MoeLoadBalancerConfig"],
@ -108,6 +109,9 @@ BASE_ZMQ_CLASSES = {
],
"torch._utils": ["_rebuild_tensor_v2"],
"torch.storage": ["_load_from_bytes"],
"transformers.tokenization_utils_fast": ["PreTrainedTokenizerFast"],
"tokenizers": ["Tokenizer", "AddedToken"],
"tokenizers.models": ["Model"],
}

2
tests/integration/test_lists/waives.txt
View File

@ -452,8 +452,6 @@ perf/test_perf.py::test_perf[qwen_14b_chat-cppmanager-exe-plugin_ifb-float16-inp
perf/test_perf.py::test_perf[llama_v3.1_70b-bench-bfloat16-input_output_len:1024,1024-tp:2-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5295411)
perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-bfloat16-input_output_len:128,128-quant:int8-gpus:2] SKIP (https://nvbugspro.nvidia.com/bug/5295411)
perf/test_perf.py::test_perf[starcoder2_3b-bench-pytorch-float16-input_output_len:512,200] SKIP (https://nvbugspro.nvidia.com/bug/5295411)
test_e2e.py::test_trtllm_bench_llmapi_launch[pytorch_backend-llama-v3-llama3-8b] SKIP (https://nvbugs/5302895)
test_e2e.py::test_trtllm_bench_llmapi_launch[trt_backend-llama-v3-llama3-8b] SKIP (https://nvbugs/5302895)
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[False] SKIP (https://nvbugs/5303573)
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[True] SKIP (https://nvbugs/5303573)
test_e2e.py::test_openai_multi_chat_example SKIP (https://nvbugs/5236980)

1
tests/unittest/llmapi/test_llm_multi_gpu.py
View File

@ -334,7 +334,6 @@ def test_llm_multi_node_pytorch(nworkers: int):
@skip_single_gpu
def test_llm_multi_node_with_postproc():
pytest.skip(reason="https://nvbugs/5302891")
nworkers = 2
test_case_file = os.path.join(os.path.dirname(__file__),
"run_llm_with_postproc.py")