[XPU] Fix Nemotron FP8 LM-eval config: drop CUDA-only moe_backend and wire to new Buildkite job (#49685)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
@@ -26,3 +26,27 @@ steps:
|
||||
'uv pip install "gpt-oss[eval]==0.0.5" &&
|
||||
cd tests &&
|
||||
pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-xpu.txt'
|
||||
- label: LM Eval Large Models(2 GPUs)
|
||||
key: lm-eval-large-models-2-gpus
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 2+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
optional: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- .buildkite/lm-eval-harness/
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd .buildkite/lm-eval-harness &&
|
||||
export VLLM_USE_DEEP_GEMM=0 &&
|
||||
pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large-xpu-fp8.txt --tp-size=2'
|
||||
|
||||
@@ -0,0 +1,16 @@
|
||||
model_name: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.7142
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.4579
|
||||
limit: 256
|
||||
num_fewshot: 5
|
||||
max_model_len: 262144
|
||||
kv_cache_dtype: fp8
|
||||
enforce_eager: true
|
||||
apply_chat_template: true
|
||||
fewshot_as_multiturn: true
|
||||
trust_remote_code: true
|
||||
@@ -0,0 +1 @@
|
||||
NVIDIA-Nemotron-3-Nano-30B-A3B-FP8-xpu.yaml
|
||||
Reference in New Issue
Block a user