2025-12-16 14:28:34 -05:00
|
|
|
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}'
|
2026-02-25 20:44:44 -05:00
|
|
|
--moe-backend=flashinfer_trtllm
|
