Files
vllm/tests/evals/gsm8k/configs/Qwen3-Next-80B-A3B-NVFP4-EP2.yaml
2026-02-25 17:44:44 -08:00

12 lines
344 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}'
--moe-backend=flashinfer_trtllm