TensorRT-LLMs/tests/integration/test_lists/test-db
Bo Li 5ea6888dda
[https://nvbugs/5810940][fix] Update lm_eval to 4.9.10 and re-enable Skip Softmax Attention tests on CI. (#11176)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
Co-authored-by: Tian Zheng <29906817+Tom-Zheng@users.noreply.github.com>
2026-02-11 00:54:40 -05:00
..
l0_a10.yml [TRTLLM-9527][feat] Modularization of the transceiver for KV manager v2 (step 4) (#11225) 2026-02-06 07:15:18 -05:00
l0_a30.yml [TRTLLM-9735][feat] Add processed logprobs functionality to TorchSampler (#9675) 2026-01-16 10:52:41 -08:00
l0_a100.yml [https://nvbugs/5759698][fix] unwaive test_base_worker (#10669) 2026-01-20 21:14:03 -05:00
l0_b200.yml [https://nvbugs/5810940][fix] Update lm_eval to 4.9.10 and re-enable Skip Softmax Attention tests on CI. (#11176) 2026-02-11 00:54:40 -05:00
l0_b300.yml [https://nvbugs/5640873][fix] Move thop tests to pre-merge (#9094) 2025-11-13 13:08:13 +08:00
l0_dgx_b200_multi_nodes_disagg_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu8.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_dgx_b200_perf_sanity.yml [https://nvbugs/5820874][fix] Adjust deepgemm tuning buckets to cover larger num_tokens's scope (#11259) 2026-02-05 23:12:38 +08:00
l0_dgx_b200.yml [https://nvbugs/5810940][fix] Update lm_eval to 4.9.10 and re-enable Skip Softmax Attention tests on CI. (#11176) 2026-02-11 00:54:40 -05:00
l0_dgx_b300.yml [TRTLLM-9111][feat] provide the uniform test framework to test all MoE backends (#11128) 2026-02-04 15:57:56 +08:00
l0_dgx_h100.yml [TRTLLM-10273][feat] Move MambaCacheManager from Python to C++ (#10540) 2026-02-10 07:20:56 -08:00
l0_dgx_h200.yml [None][infra] Waive failed cases for main on 01/19 (#10794) 2026-01-19 00:55:26 -05:00
l0_gb10.yml [None][infra] Enable single-gpu CI on spark (#9304) 2025-12-30 17:22:14 +08:00
l0_gb200_multi_gpus_perf_sanity.yml [TRTLLM-8263][feat] Add Aggregated Perf Tests (#10598) 2026-01-17 13:16:36 +08:00
l0_gb200_multi_gpus.yml [TRTLLM-9766][feat] Integration of the KVCacheManager V2 to TRTLLM Runtime (#10659) 2026-02-02 14:29:02 +08:00
l0_gb200_multi_nodes_aggr_perf_sanity_node2_gpu8.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_gb200_multi_nodes_disagg_perf_sanity_ctx1_node1_gpu1_gen1_node1_gpu4.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_gb200_multi_nodes_disagg_perf_sanity_ctx1_node1_gpu1_gen1_node2_gpu8.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_gb200_multi_nodes_disagg_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu4.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_gb200_multi_nodes_disagg_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_gb200_multi_nodes_disagg_perf_sanity_ctx1_node1_gpu4_gen1_node4_gpu16.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_gb200_multi_nodes_disagg_perf_sanity_ctx1_node1_gpu4_gen1_node8_gpu32.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_gb200_multi_nodes_disagg_perf_sanity_ctx1_node2_gpu8_gen1_node2_gpu8.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_gb200_multi_nodes_disagg_perf_sanity_ctx1_node2_gpu8_gen1_node4_gpu16.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_gb200_multi_nodes_disagg_perf_sanity_ctx1_node2_gpu8_gen1_node8_gpu32.yml [TRTLLM-8263][feat] Add Disagg Perf Tests (#10912) 2026-02-04 10:16:11 +08:00
l0_gb200_multi_nodes.yml [https://nvbugs/5715568][fix] Force release torch memory when LLM is destroyed (#10314) 2026-01-05 15:30:18 +08:00
l0_gb202.yml [TRTLLM-9831][perf] Enable 2CTA with autotune for CuteDSL MoE and Grouped GEMM optimizations (#10201) 2025-12-25 09:04:20 -05:00
l0_gb203.yml [TRTLLM-5277] chore: refine llmapi examples for 1.0 (part1) (#5431) 2025-07-01 19:06:41 +08:00
l0_gb300_multi_gpus.yml [TRTLLM-9111][feat] provide the uniform test framework to test all MoE backends (#11128) 2026-02-04 15:57:56 +08:00
l0_gb300.yml [TRTLLM-9766][feat] Integration of the KVCacheManager V2 to TRTLLM Runtime (#10659) 2026-02-02 14:29:02 +08:00
l0_gh200.yml [None][test] Update llm_models_root to improve path handling on BareMetal environment (#7876) 2025-09-24 17:35:57 +08:00
l0_h100.yml [None][chore] Move test_trtllm_flashinfer_symbol_collision.py to tests/unittest/_torch (#11168) 2026-02-09 13:57:57 +08:00
l0_l40s.yml [TRTLLM-9522][feat] support image_embeds in OpenAI API (#9715) 2026-01-14 10:31:03 +01:00
l0_perf.yml [#10607][chore] Add Nemotron Nano v3 FP8 autodeploy perf test (#10603) 2026-01-19 08:48:07 +02:00
l0_rtx_pro_6000.yml [TRTLLM-9766][feat] Integration of the KVCacheManager V2 to TRTLLM Runtime (#10659) 2026-02-02 14:29:02 +08:00
l0_sanity_check.yml [None][ci] Remove long-running sanity check tests on GH200 (#10924) (#10969) 2026-01-24 13:06:28 +08:00
README.md Update (#2978) 2025-03-23 16:39:35 +08:00

Description

This folder contains test definition which is consumed by trt-test-db tool based on system specifications.

Installation

Install trt-test-db using the following command:

pip3 install --extra-index-url https://urm.nvidia.com/artifactory/api/pypi/sw-tensorrt-pypi/simple --ignore-installed trt-test-db==1.8.5+bc6df7

Test Definition

Test definitions are stored in YAML files located in ${TRT_LLM_ROOT}/tests/integration/test_lists/test-db/. These files define test conditions and the tests to be executed.

Example YAML Structure

version: 0.0.1
l0_e2e:
  - condition:
      terms:
        supports_fp8: true
      ranges:
        system_gpu_count:
          gte: 4
          lte: 4
      wildcards:
        gpu:
          - '*h100*'
        linux_distribution_name: ubuntu*
    tests:
      - examples/test_llama.py::test_llm_llama_v3_1_1node_multi_gpus[llama-3.1-8b-enable_fp8]
      - examples/test_llama.py::test_llm_llama_v3_1_1node_multi_gpus[llama-3.1-70b-enable_fp8]

Generating Test Lists

Use trt-test-db to generate a test list based on the system configuration:

trt-test-db -d /TensorRT-LLM/src/tests/integration/test_lists/test-db \
            --context l0_e2e \
            --test-names \
            --output /TensorRT-LLM/src/l0_e2e.txt \
            --match-exact '{"chip":"ga102gl-a","compute_capability":"8.6","cpu":"x86_64","gpu":"A10","gpu_memory":"23028.0","host_mem_available_mib":"989937","host_mem_total_mib":"1031949","is_aarch64":false,"is_linux":true,"linux_distribution_name":"ubuntu","linux_version":"22.04","supports_fp8":false,"supports_int8":true,"supports_tf32":true,"sysname":"Linux","system_gpu_count":"1",...}'

This command generates a test list file (l0_e2e.txt) based on the specified context and system configuration.

Running Tests

Execute the tests using pytest with the generated test list:

pytest -v --test-list=/TensorRT-LLM/src/l0_e2e.txt --output-dir=/tmp/logs

This command runs the tests specified in the test list and outputs the results to the specified directory.

Additional Information

  • The --context parameter in the trt-test-db command specifies which context to search in the YAML files.
  • The --match-exact parameter provides system information used to filter tests based on the conditions defined in the YAML files.
  • Modify the YAML files to add or update test conditions and test cases as needed. For more detailed information on trt-test-db and pytest usage, refer to their respective documentation.