Signed-off-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Robert Shaw <robshaw@redhat.com>
9 lines
250 B
YAML
9 lines
250 B
YAML
model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
|
|
accuracy_threshold: 0.88
|
|
num_questions: 1319
|
|
num_fewshot: 5
|
|
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"
|
|
env:
|
|
VLLM_USE_DEEP_GEMM: "1"
|
|
VLLM_USE_DEEP_GEMM_MOE: "1"
|