13 lines
350 B
YAML
13 lines
350 B
YAML
|
model_name: "nm-testing/Qwen3-Next-80B-A3B-Instruct-NVFP4"
|
||
|
|
accuracy_threshold: 0.75
|
||
|
|
num_questions: 1319
|
||
|
|
num_fewshot: 5
|
||
|
|
server_args: >-
|
||
|
|
--enforce-eager
|
||
|
|
--max-model-len 4096
|
||
|
|
--tensor-parallel-size 2
|
||
|
|
--enable-expert-parallel
|
||
|
|
--speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":1}'
|
||
|
|
env:
|
||
|
|
VLLM_USE_FLASHINFER_MOE_FP4: "1"
|