Skip to content

[https://nvbugs/5601682][fix] unwaive test_disaggregated_deepseek_v3_… #8888

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
bo-nv merged 3 commits into from
Nov 5, 2025
Merged

[https://nvbugs/5601682][fix] unwaive test_disaggregated_deepseek_v3_… #8888

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ef04cb5
[https://nvbugs/5601682][fix] unwaive test_disaggregated_deepseek_v3_…
bo-nv Nov 3, 2025
4d04267
fix
bo-nv Nov 3, 2025
4e6038a
fix
bo-nv Nov 4, 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
2 changes: 1 addition & 1 deletion 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 @@ -985,7 +985,7 @@ def test_chunked_prefill(self):


@skip_pre_blackwell
@pytest.mark.timeout(DEFAULT_TEST_TIMEOUT)
@pytest.mark.timeout(3600)
class TestQwen3_30B_A3B(LlmapiAccuracyTestHarness):
FP4_MODEL = f"{llm_models_root()}/Qwen3/saved_models_Qwen3-30B-A3B_nvfp4_hf"
FP8_MODEL = f"{llm_models_root()}/Qwen3/saved_models_Qwen3-30B-A3B_fp8_hf"
Expand Down
13 changes: 4 additions & 9 deletions tests/integration/defs/disaggregated/test_disaggregated.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1289,8 +1289,7 @@ def run_disaggregated_benchmark(example_dir,
random_input_len=16,
random_output_len=64,
num_prompts=100,
max_concurrency=32,
skip_warmup=False):
max_concurrency=32):
"""Run disaggregated test with given configuration."""
run_env = env.copy()
run_env["UCX_TLS"] = "^ib"
Expand Down Expand Up @@ -1320,7 +1319,7 @@ def run_disaggregated_benchmark(example_dir,
stderr=subprocess.STDOUT,
env=run_env,
cwd=cwd) as server_proc):
# Ensure the sever has started

client_dir = f"{example_dir}/clients"
client_cmd = [
'python3', f'{client_dir}/disagg_client.py', '-c',
Expand All @@ -1329,7 +1328,7 @@ def run_disaggregated_benchmark(example_dir,
'--server-start-timeout',
str(server_start_timeout)
]
# Warm up
# Ensure the sever has started and workers are ready
check_call(client_cmd,
env=env,
poll_procs=[workers_proc, server_proc])
Expand Down Expand Up @@ -1366,9 +1365,6 @@ def run_disaggregated_benchmark(example_dir,
'--percentile-metrics',
'e2el,ttft',
]
# warm up
if not skip_warmup:
check_call(benchmark_cmd, env=env)
output = check_output(benchmark_cmd, env=env)
e2el_pattern = r"Median E2EL \(ms\):\s*(\d+\.?\d*)"
ttft_pattern = r"Median TTFT \(ms\):\s*(\d+\.?\d*)"
Expand Down Expand Up @@ -1513,8 +1509,7 @@ def test_disaggregated_deepseek_v3_lite_bf16_empty_batch(
num_prompts=10,
max_concurrency=10,
random_input_len=384,
random_output_len=1536,
skip_warmup=True)
random_output_len=1536)
print(f"E2EL: {e2el} ms, TTFT: {ttft} ms")

assert e2el > 0 and ttft > 0
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 @@ -338,7 +338,6 @@ triton_server/test_triton_llm.py::test_llmapi_backend[4-0-disableDecoupleMode-te
triton_server/test_triton_llm.py::test_llmapi_backend[1-0-disableDecoupleMode-tensorrt_llm] SKIP (https://nvbugs/5461874)
triton_server/test_triton_llm.py::test_llmapi_backend[1-0-enableDecoupleMode-tensorrt_llm] SKIP (https://nvbugs/5461874)
cpp/test_e2e.py::test_benchmarks[gpt-80] SKIP (https://nvbugs/5601670)
disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_bf16_empty_batch[DeepSeek-V3-Lite-bf16] SKIP (https://nvbugs/5601682)
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[llama-v3-8b-hf] SKIP (https://nvbugs/5587574)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm-fp8] SKIP (https://nvbugs/5608790)
full:H20-3e/accuracy/test_llm_api_pytorch.py::TestNemotronUltra::test_auto_dtype[tp8ep4-cuda_graph=True] SKIP (slow I/O)
Expand Down