TensorRT-LLMs/tests/integration/test_lists/test-db
Balaram Buddharaju dcd3f7b5ea
[https://nvbugs/5744427][fix] Fix accuracy test OOM (#10173)
Signed-off-by: Balaram Buddharaju <169953907+brb-nv@users.noreply.github.com>
2025-12-21 02:03:38 -05:00
..
l0_a10.yml [https://nvbugs/5722653][fix] Address port conflict by assigning different port section in the same node. (#10035) 2025-12-19 15:34:04 +08:00
l0_a30.yml [TRTLLM-7967][feat] Adding Starcoder2 PyTorch Backend Support (#8923) 2025-11-24 11:23:22 -08:00
l0_a100.yml [https://nvbugs/5606136][ci] Remove tests for deprecating triton multimodal models. (#8926) 2025-11-06 17:58:42 -08:00
l0_b200.yml [TRTLLM-8961][feat] ConfigurableMoE support DeepGemm (#9858) 2025-12-15 10:47:15 +08:00
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_perf_sanity.yml [TRTLLM-9000][feat] Add multi-node Perf Tests into CI (#8800) 2025-12-08 09:00:44 +08:00
l0_dgx_b200.yml [https://nvbugs/5741331][fix] Fix helix accuracy test (#10021) 2025-12-18 15:27:53 -08:00
l0_dgx_b300_perf_sanity.yml [TRTLLM-9000][feat] Add multi-node Perf Tests into CI (#8800) 2025-12-08 09:00:44 +08:00
l0_dgx_b300.yml [None][chore] remove qwen3-next accuracy tests (#9534) 2025-12-01 11:49:37 +08:00
l0_dgx_h100.yml [None][feat] Support Mooncake transfer engine as a cache transceiver backend (#8309) 2025-12-19 10:09:51 +08:00
l0_dgx_h200.yml [TRTLLM-9416][feat] Skip DS-v3.2 indexer MQA and Top-K for short sequences. (#9524) 2025-12-15 12:42:25 +08:00
l0_gb200_multi_gpus_perf_sanity.yml [https://nvbugs/5727481][ci] Fix Port Conflict in Perf-Sanity CI Test (#9896) 2025-12-12 17:16:50 +08:00
l0_gb200_multi_gpus.yml [https://nvbugs/5741331][fix] Fix helix accuracy test (#10021) 2025-12-18 15:27:53 -08:00
l0_gb200_multi_nodes_perf_sanity.yml [TRTLLM-9000][feat] Add multi-node Perf Tests into CI (#8800) 2025-12-08 09:00:44 +08:00
l0_gb200_multi_nodes.yml [None][chore] Weekly mass integration of release/1.1 -- rebase (#9522) 2025-11-29 21:48:48 +08:00
l0_gb202.yml [None][feat] Update TRTLLM MoE MxFP4 cubins; autotune tileN (#8156) 2025-10-23 09:14:18 +08:00
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 [None][feat] Enable EPLB for trtllm-gen and cutlass backend (#8886) 2025-11-12 12:30:27 -08:00
l0_gb300.yml [TRTLLM-8971][infra] Update gpu key for B300/GB300 (#8724) 2025-10-29 20:36:44 -07:00
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 [https://nvbugs/5744427][fix] Fix accuracy test OOM (#10173) 2025-12-21 02:03:38 -05:00
l0_l40s.yml [TRTLLM-8310][feat] Add Qwen3-VL-MoE (#9689) 2025-12-15 20:05:20 -08:00
l0_perf.yml [#7288][feat] Added AutoDeploy backend support to test_perf.py (#7588) 2025-09-28 21:21:27 -07:00
l0_rtx_pro_6000.yml [https://nvbugs/5567586][feat] Ampere xqa swa specdec for GPT-OSS Eagle3-one-model (#8383) 2025-12-08 11:16:05 -08:00
l0_sanity_check.yml [None][fix] Fix ready signal in NIXL backend (#10000) 2025-12-19 09:43:40 +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.