TensorRT-LLMs/tests/integration/test_lists/test-db
Chuang Zhu 44c70c88f9
chore:[BREAKING CHANGE] use cacheTransceiverConfig as knobs for disagg service (#5234)
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
2025-07-17 17:42:07 +08:00
..
l0_a10.yml [fix] Fix mistral unit tests due to transformers upgrade (#5904) 2025-07-10 10:45:27 -07:00
l0_a30.yml feat: TRTLLM-5574 Add phi-4-multimodal pytorch-backend support (#5644) 2025-07-17 06:30:58 +08:00
l0_a100.yml [Infra] - Set default timeout to 1hr and remove some specific settings (#5667) 2025-07-02 08:37:54 -04:00
l0_b200.yml [nvbug 5300551] test: increase block count in eviction test (#5465) 2025-07-04 13:14:13 +08:00
l0_dgx_b200.yml test: Update Llama4 Scout FP4 & FP8 accuracy tests (#5901) 2025-07-17 09:41:18 +08:00
l0_dgx_h100.yml chore:[BREAKING CHANGE] use cacheTransceiverConfig as knobs for disagg service (#5234) 2025-07-17 17:42:07 +08:00
l0_dgx_h200.yml [ci] small multigpu speedups (#5643) 2025-07-03 08:06:10 -04:00
l0_gb200_multi_nodes.yml test: add more tests for GB200 with 8 GPUs/2 nodes in L0 tests (#5397) 2025-07-04 13:14:13 +08:00
l0_gb200.yml test: Move some of the test from post merge to pre-merge, update dgx b200 test case (#5640) 2025-07-14 17:17:30 +08:00
l0_gb202.yml [fix] WAR to fix the illegal memory access issue in moe gemm on SM120 (#5636) 2025-07-10 09:20:30 +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_gh200.yml [Infra] - Set default timeout to 1hr and remove some specific settings (#5667) 2025-07-02 08:37:54 -04:00
l0_h100.yml [fix] Release slots with spec decode + disagg (#5975) (#6032) 2025-07-17 12:58:18 +08:00
l0_l40s.yml feat: TRTLLM-5574 Add phi-4-multimodal pytorch-backend support (#5644) 2025-07-17 06:30:58 +08:00
l0_perf.yml CI: Performance regression tests update (#3531) 2025-06-01 09:47:55 +03:00
l0_rtx_pro_6000.yml feat: Add deepseek-lite tests for RTX pro 6000 (#5903) 2025-07-16 15:51:45 +08:00
l0_sanity_check.yml [TRTLLM-6160] chore: add sampling examples for pytorch (#5951) 2025-07-14 15:28:32 +09:00
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.