Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
12 lines
344 B
YAML
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
|