group: LM Eval
depends_on: 
  - image-build
steps:
- label: LM Eval Small Models
  timeout_in_minutes: 75
  source_file_dependencies:
  - csrc/
  - vllm/model_executor/layers/quantization
  autorun_on_main: true
  commands:
  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt

- label: LM Eval Large Models (4 GPUs)(A100)
  gpu: a100
  optional: true
  num_gpus: 4
  working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
  source_file_dependencies:
  - csrc/
  - vllm/model_executor/layers/quantization
  commands:
  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
  - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large.txt --tp-size=4

- label: LM Eval Large Models (4 GPUs)(H100)
  gpu: h100
  optional: true
  num_gpus: 4
  working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
  source_file_dependencies:
  - csrc/
  - vllm/model_executor/layers/quantization
  commands:
    - export VLLM_USE_DEEP_GEMM=0  # We found Triton is faster than DeepGEMM for H100
    - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large-hopper.txt --tp-size=4

- label: LM Eval Small Models (B200)
  timeout_in_minutes: 120
  gpu: b200
  optional: true
  source_file_dependencies:
  - csrc/
  - vllm/model_executor/layers/quantization
  commands:
  - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt