Skip to content

Unwaive disaggregated serving accuracy tests #5095

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 1 commit into from
Jun 18, 2025
Merged

Unwaive disaggregated serving accuracy tests #5095

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
31 changes: 12 additions & 19 deletions tests/integration/defs/accuracy/test_disaggregated_serving.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ def __exit__(self, exc_type, exc_val, exc_tb):

for future in self.futures:
future.cancel()
self.shutdown(wait=False, cancel_futures=True)
self.shutdown(wait=True, cancel_futures=True)
return False


Expand Down Expand Up @@ -163,15 +163,16 @@ def generate_async(prompt: str,
thread_pool.futures.append(future)
return future

yield DuckLLM(args, generate_async)
try:
yield DuckLLM(args, generate_async)
finally:
ctx_server.terminate()
gen_server.terminate()
disaggregated_server.terminate()

ctx_server.terminate()
gen_server.terminate()
disaggregated_server.terminate()

ctx_server.wait()
gen_server.wait()
disaggregated_server.wait()
ctx_server.wait()
gen_server.wait()
disaggregated_server.wait()


@pytest.mark.timeout(3600)
Expand Down Expand Up @@ -252,16 +253,8 @@ class TestDeepSeekV3Lite(LlmapiAccuracyTestHarness):
@parametrize_with_ids("mtp_nextn",
[0, pytest.param(2, marks=skip_pre_hopper)])
def test_auto_dtype(self, overlap_scheduler, mtp_nextn):
ctx_server_config = {
"pytorch_backend_config": {
"disable_overlap_scheduler": True
}
}
gen_server_config = {
"pytorch_backend_config": {
"disable_overlap_scheduler": not overlap_scheduler
}
}
ctx_server_config = {"disable_overlap_scheduler": True}
gen_server_config = {"disable_overlap_scheduler": not overlap_scheduler}
if mtp_nextn > 0:
ctx_server_config["speculative_config"] = {
"decoding_type": "MTP",
Expand Down
6 changes: 2 additions & 4 deletions tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -402,10 +402,6 @@ test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-70B-FP8-llama-3.1-model/Llama
test_e2e.py::test_ptp_quickstart_advanced_ngram[Llama-3.1-8B-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct] SKIP (https://nvbugspro.nvidia.com/bug/5324239)
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp2pp2-attn_backend=TRTLLM-torch_compile=False] SKIP (https://nvbugs/5318143)
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp2pp2-attn_backend=TRTLLM-torch_compile=True] SKIP (https://nvbugs/5318143)
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=False] SKIP (https://nvbugs/5322354)
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=True] SKIP (https://nvbugs/5322354)
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=False] SKIP (https://nvbugs/5322354)
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=True] SKIP (https://nvbugs/5322354)
test_e2e.py::test_ptp_quickstart_advanced[Nemotron-H-8B-Nemotron-H-8B-Base-8K] SKIP (https://nvbugs/5325284)
test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-70B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-70B] SKIP (https://nvbugs/5323316)
disaggregated/test_disaggregated.py::test_disaggregated_single_gpu_with_mpirun[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/5328160)
Expand All @@ -416,6 +412,8 @@ test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-NVFP4-nvfp4-quantized/Meta
test_e2e.py::test_ptp_quickstart_advanced[Mixtral-8x7B-NVFP4-nvfp4-quantized/Mixtral-8x7B-Instruct-v0.1] SKIP (https://nvbugs/5333659)
test_e2e.py::test_ptp_quickstart_advanced[Nemotron-Super-49B-v1-NVFP4-nvfp4-quantized/Llama-3_3-Nemotron-Super-49B-v1_nvfp4_hf] SKIP (https://nvbugs/5333659)
examples/test_multimodal.py::test_llm_multimodal_general[Mistral-Small-3.1-24B-Instruct-2503-pp:1-tp:1-bfloat16-bs:8-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5331031)
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=True] SKIP (https://nvbugs/5322354)
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=True] SKIP (https://nvbugs/5322354)
accuracy/test_disaggregated_serving.py::TestLlama4ScoutInstruct::test_auto_dtype[True] SKIP (https://nvbugs/5336321)
accuracy/test_disaggregated_serving.py::TestLlama4ScoutInstruct::test_auto_dtype[False] SKIP (https://nvbugs/5336321)
full:B200/examples/test_gemma.py::test_llm_gemma_1gpu_summary_vswa[gemma-3-1b-it-other-bfloat16-8] SKIP (https://nvbugs/5292737)
Expand Down