Signed-off-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Robert Shaw <robshaw@redhat.com>
11 lines
324 B
YAML
11 lines
324 B
YAML
model_name: "RedHatAI/Qwen3-30B-A3B-FP8-block"
|
|
accuracy_threshold: 0.85
|
|
num_questions: 1319
|
|
num_fewshot: 5
|
|
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"
|
|
env:
|
|
VLLM_USE_DEEP_GEMM: "0"
|
|
VLLM_USE_DEEP_GEMM_MOE: "0"
|
|
VLLM_USE_FLASHINFER_MOE_FP8: "1"
|
|
VLLM_FLASHINFER_MOE_BACKEND: "throughput"
|