Skip to content

[None][fix] Raise server_waiting_timeout to 3600s for DSv4 disagg tests #14028

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
lfr-0531 merged 2 commits into from
May 12, 2026
Merged

[None][fix] Raise server_waiting_timeout to 3600s for DSv4 disagg tests #14028

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
09dfa59
[None][fix] Raise server_waiting_timeout to 3600s for DSv4 disagg tests
Shixiaowei02 May 12, 2026
8410783
Revert "[None][chore] waive TestDeepSeekV4Flash::test_auto_dtype (#14…
Shixiaowei02 May 12, 2026
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
14 changes: 10 additions & 4 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 @@ -2269,9 +2269,12 @@ def test_auto_dtype(self):
"num_instances": 1
},
}
# V4-Flash 148GB weight prefetch + warmup needs >35 min, default wait timeout times out.
with launch_disaggregated_llm(disaggregated_server_config,
ctx_server_config, gen_server_config,
self.MODEL_PATH) as llm:
ctx_server_config,
gen_server_config,
self.MODEL_PATH,
server_waiting_timeout=3600) as llm:
task = MMLU(self.MODEL_NAME)
task.evaluate(llm, is_integration_test=True)

Expand Down Expand Up @@ -2330,8 +2333,11 @@ def test_auto_dtype(self):
"num_instances": 1
},
}
# Same long-init reason as TestDeepSeekV4Flash above.
with launch_disaggregated_llm(disaggregated_server_config,
ctx_server_config, gen_server_config,
self.MODEL_PATH) as llm:
ctx_server_config,
gen_server_config,
self.MODEL_PATH,
server_waiting_timeout=3600) as llm:
task = MMLU(self.MODEL_NAME)
task.evaluate(llm, is_integration_test=True)
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 @@ -430,4 +430,3 @@ disaggregated/test_disaggregated.py::test_disaggregated_gpt_oss_120b_harmony[gpt
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-dp4-cutlass-auto] SKIP (https://nvbugs/5596343)
unittest/_torch/speculative/test_eagle3.py::test_llama_eagle3_dynamic_tree[True-False] SKIP (https://nvbugs/6113021)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV4Flash::test_nvfp4_4gpus_static_eplb[moe_backend=TRTLLM] SKIP (worker init CUDA error masked by kv_cache_manager_v2/_exceptions.py:49 cuGetErrorString type bug; real failure unreadable until that wrapper is fixed)
accuracy/test_disaggregated_serving.py::TestDeepSeekV4Flash::test_auto_dtype SKIP (https://nvbugs/6166283)
Loading