7350331718
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com> Signed-off-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Robert Shaw <robshaw@redhat.com>
9 lines
282 B
YAML
9 lines
282 B
YAML
model_name: "nvidia/Qwen3-30B-A3B-NVFP4"
|
|
accuracy_threshold: 0.88
|
|
num_questions: 1319
|
|
num_fewshot: 5
|
|
server_args: "--enforce-eager --max-model-len 8192 --data-parallel-size 2 --enable-expert-parallel"
|
|
env:
|
|
VLLM_USE_FLASHINFER_MOE_FP4: "1"
|
|
VLLM_FLASHINFER_MOE_BACKEND: "latency"
|