9 lines
339 B
YAML
9 lines
339 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 --data-parallel-size 2 --enable-expert-parallel --all2all-backend deepep_low_latency --disable-uvicorn-access-log"
|
|
env:
|
|
VLLM_USE_DEEP_GEMM: "1"
|
|
VLLM_USE_DEEP_GEMM_MOE: "1"
|