Skip to content

[TRTLLM-13948][test] Add DeepSeek R1/V3.2/V3-Lite disaggregated accuracy tests #16344

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
nv-xtf merged 6 commits into from
Jul 24, 2026
+125 −5
Merged

[TRTLLM-13948][test] Add DeepSeek R1/V3.2/V3-Lite disaggregated accuracy tests #16344

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
b30b023
[TRTLLM-13948][test] Add DeepSeek R1/V3.2/V3-Lite disaggregated accur…
asfiyab-nvidia Jul 13, 2026
2c93e52
changes:
asfiyab-nvidia Jul 14, 2026
3749952
disable autotuner for DeepSeekR1 test
asfiyab-nvidia Jul 15, 2026
2f3cd02
address comments
asfiyab-nvidia Jul 19, 2026
56f434e
pre-commit run formatting
asfiyab-nvidia Jul 20, 2026
762de1a
Update memory guard to 200000
asfiyab-nvidia Jul 23, 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
126 changes: 121 additions & 5 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 @@ -1376,15 +1376,12 @@ def test_kv_cache_v2_nixl_python(self):
}
disaggregated_server_config = {
"hostname": "localhost",
"port": 8000,
"backend": "pytorch",
"context_servers": {
"num_instances": 1,
"urls": ["localhost:8001"]
"num_instances": 1
},
"generation_servers": {
"num_instances": 1,
"urls": ["localhost:8002"]
"num_instances": 1
}
}
with launch_disaggregated_llm(disaggregated_server_config,
Expand Down Expand Up @@ -1752,6 +1749,62 @@ def test_auto_dtype(self, overlap_scheduler):
model_name=self.MODEL_NAME,
test_sets=["MMLU", "GSM8K"])

@pytest.mark.skip_less_device(4)
@pytest.mark.skip_less_device_memory(200000)
@pytest.mark.parametrize("use_kv_cache_manager_v2", [False],
ids=["cache_mgr_v1"])
def test_kv_cache_v2_nixl_python(self, use_kv_cache_manager_v2):
Comment thread
nv-xtf marked this conversation as resolved.
"""Test with KV cache manager v1, block_reuse=False, backend=NIXL, transceiver_runtime=PYTHON."""
max_num_tokens = 8192
moe_config = {"backend": "TRTLLM", "max_num_tokens": max_num_tokens}
ctx_server_config = {
"disable_overlap_scheduler": True,
"kv_cache_config": {
"free_gpu_memory_fraction": 0.5,
"enable_block_reuse": False,
"use_kv_cache_manager_v2": use_kv_cache_manager_v2
},
"cache_transceiver_config": {
"backend": "NIXL",
"transceiver_runtime": "PYTHON",
"max_tokens_in_buffer": 4096
},
"tensor_parallel_size": 2,
"moe_expert_parallel_size": 2,
"enable_autotuner": False,
}
gen_server_config = {
"disable_overlap_scheduler": False,
"moe_config": moe_config,
"kv_cache_config": {
"free_gpu_memory_fraction": 0.5,
"enable_block_reuse": False,
"use_kv_cache_manager_v2": use_kv_cache_manager_v2
},
"cache_transceiver_config": {
"backend": "NIXL",
"transceiver_runtime": "PYTHON",
"max_tokens_in_buffer": 4096
},
"tensor_parallel_size": 2,
"moe_expert_parallel_size": 2,
"enable_autotuner": False,
}
disaggregated_server_config = {
"hostname": "localhost",
"backend": "pytorch",
"context_servers": {
"num_instances": 1,
},
"generation_servers": {
"num_instances": 1,
}
}
with launch_disaggregated_llm(disaggregated_server_config,
ctx_server_config, gen_server_config,
self.MODEL_PATH) as llm:
run_accuracy_test(llm, self.MODEL_NAME, ["GSM8K"])


@pytest.mark.timeout(DEFAULT_TEST_TIMEOUT)
@skip_pre_hopper
Expand Down Expand Up @@ -2605,3 +2658,66 @@ def test_auto_dtype(self):
server_waiting_timeout=3600) as llm:
task = MMLU(self.MODEL_NAME)
task.evaluate(llm, is_integration_test=True)


@pytest.mark.timeout(DEFAULT_TEST_TIMEOUT)
@skip_pre_blackwell
@pytest.mark.skip_less_device_memory(200000)
class TestDeepSeekR1(LlmapiAccuracyTestHarness):
Comment thread
crazydemo marked this conversation as resolved.
MODEL_NAME = "deepseek-ai/DeepSeek-R1"
MODEL_PATH = f"{llm_models_root()}/DeepSeek-R1/DeepSeek-R1-0528-FP4-v2"

@pytest.mark.skip_less_device(4)
@pytest.mark.parametrize("use_kv_cache_manager_v2", [False],
ids=["cache_mgr_v1"])
def test_kv_cache_v2_nixl_python(self, use_kv_cache_manager_v2):
"""Test with KV cache manager v1, block_reuse=False, backend=NIXL, transceiver_runtime=PYTHON."""
max_num_tokens = 8192
moe_config = {"backend": "TRTLLM", "max_num_tokens": max_num_tokens}
ctx_server_config = {
"disable_overlap_scheduler": True,
"kv_cache_config": {
"free_gpu_memory_fraction": 0.5,
"enable_block_reuse": False,
"use_kv_cache_manager_v2": use_kv_cache_manager_v2
},
"cache_transceiver_config": {
"backend": "NIXL",
"transceiver_runtime": "PYTHON",
"max_tokens_in_buffer": 4096
},
"tensor_parallel_size": 2,
"moe_expert_parallel_size": 2,
"enable_autotuner": False,
}
gen_server_config = {
"disable_overlap_scheduler": False,
"moe_config": moe_config,
"kv_cache_config": {
"free_gpu_memory_fraction": 0.5,
"enable_block_reuse": False,
"use_kv_cache_manager_v2": use_kv_cache_manager_v2
},
"cache_transceiver_config": {
"backend": "NIXL",
"transceiver_runtime": "PYTHON",
"max_tokens_in_buffer": 4096
},
"tensor_parallel_size": 2,
"moe_expert_parallel_size": 2,
"enable_autotuner": False,
}
disaggregated_server_config = {
"hostname": "localhost",
"backend": "pytorch",
"context_servers": {
"num_instances": 1,
},
"generation_servers": {
"num_instances": 1,
}
}
with launch_disaggregated_llm(disaggregated_server_config,
ctx_server_config, gen_server_config,
self.MODEL_PATH) as llm:
run_accuracy_test(llm, self.MODEL_NAME, ["GSM8K"])
Comment thread
coderabbitai[bot] marked this conversation as resolved.
2 changes: 2 additions & 0 deletions tests/integration/test_lists/qa/llm_function_core.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,6 @@
accuracy/test_disaggregated_serving.py::TestDeepSeekR1::test_kv_cache_v2_nixl_python[cache_mgr_v1]
accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_auto_dtype[False]
accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_kv_cache_v2_nixl_python[cache_mgr_v1]
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=False]
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=True]
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=False]
Expand Down
2 changes: 2 additions & 0 deletions tests/integration/test_lists/test-db/l0_dgx_b300.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,8 @@ l0_dgx_b300:
- accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4-auto]
- accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4-fp8]
- accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_nixl_backend
- accuracy/test_disaggregated_serving.py::TestDeepSeekR1::test_kv_cache_v2_nixl_python[cache_mgr_v1]
Comment thread
nv-xtf marked this conversation as resolved.
- accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_kv_cache_v2_nixl_python[cache_mgr_v1]
- accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_nixl_backend
- accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_kv_cache_v2_nixl_python
- accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_kv_cache_v2_nixl_python
Expand Down
Loading