Skip to content

[https://nvbugs/6627979][fix] Apply chat template in test_eagle3_output_repetition_4gpus #18170

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
zhaoyangwang-nvidia merged 1 commit into from
Aug 25, 2026
Merged

[https://nvbugs/6627979][fix] Apply chat template in test_eagle3_output_repetition_4gpus #18170

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
19 changes: 17 additions & 2 deletions tests/integration/defs/test_e2e.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1948,8 +1948,23 @@ def test_eagle3_output_repetition_4gpus(model_dir: str, draft_model_dir: str):
CudaGraphConfig(),
}

# Test prompt
prompt = "Who are you?"
# Test prompt. It has to go through the chat template: a bare string makes
# the model continue arbitrary text instead of answering a turn, so it
# never emits <|im_end|> and keeps generating until it hits max_tokens --
# by which point it is looping over whatever it last said. That
# degeneration comes from the prompt, not from Eagle3, and it is what made
# this test flaky (nvbugs/6627979).
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(target_model_dir)
prompt = tokenizer.apply_chat_template(
[{
"role": "user",
"content": "Who are you?"
}],
tokenize=False,
add_generation_prompt=True,
enable_thinking=False,
)
sampling_params = SamplingParams(max_tokens=1024, temperature=0)

# Run with Eagle3
Expand Down
2 changes: 0 additions & 2 deletions tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,7 +221,6 @@ full:GB300/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_
full:GB300/accuracy/test_llm_api_pytorch_multimodal.py::TestGemma3_27BInstruct::test_fp8_prequantized SKIP (https://nvbugs/6479708)
full:GB300/disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_attention_dp_overlap[DeepSeek-V3-Lite-fp8] SKIP (https://nvbugs/6581064)
full:GB300/disaggregated/test_disaggregated.py::test_disaggregated_logprobs_serving[llama-3.1-8b-instruct] SKIP (https://nvbugs/6657522)
full:GB300/test_e2e.py::test_eagle3_output_repetition_4gpus[Qwen3/Qwen3-30B-A3B-Qwen3/Qwen3-30B-eagle3] SKIP (https://nvbugs/6627979)
full:GB300/unittest/_torch/executor/test_overlap_scheduler.py::test_overlap_scheduler_consistency[block_reuse-python_scheduler-TRTLLMSampler] SKIP (https://nvbugs/6608387)
full:GB300/unittest/_torch/executor/test_overlap_scheduler.py::test_overlap_scheduler_consistency[block_reuse-python_scheduler-TorchSampler] SKIP (https://nvbugs/6608387)
full:GB300/unittest/_torch/executor/test_overlap_scheduler.py::test_overlap_scheduler_consistency[no_reuse-cpp_scheduler-TRTLLMSampler] SKIP (https://nvbugs/6608387)
Expand All @@ -240,7 +239,6 @@ full:H100/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_a
full:H100/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[full_budget] SKIP (https://nvbugs/6597570)
full:H100/disaggregated/test_disaggregated.py::test_disaggregated_logprobs_serving[llama-3.1-8b-instruct] SKIP (https://nvbugs/6275959)
full:H100/disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-qwen3_32b_fp8_stress] SKIP (https://nvbugs/6312828)
full:H100/test_e2e.py::test_eagle3_output_repetition_4gpus[Qwen3/Qwen3-30B-A3B-Qwen3/Qwen3-30B-eagle3] SKIP (https://nvbugs/6627979)
full:H100_PCIe/unittest/llmapi/test_llm_pytorch.py::test_llama_7b_multi_lora_evict_and_reload_lora_gpu_cache SKIP (https://nvbugs/5682551)
full:H20/accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=False] SKIP (https://nvbugs/6345827)
full:H20/accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=True] SKIP (https://nvbugs/6345827)
Expand Down
Loading