12 lines
265 B
YAML
12 lines
265 B
YAML
model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
|
|
accuracy_threshold: 0.85
|
|
num_questions: 1319
|
|
num_fewshot: 5
|
|
server_args: >-
|
|
--max-model-len 4096
|
|
--tensor-parallel-size 2
|
|
--enable-expert-parallel
|
|
--async-scheduling
|
|
env:
|
|
VLLM_USE_FLASHINFER_MOE_FP8: "1"
|