Files
vllm/tests/evals/gsm8k/configs/DeepSeek-V3.2-TP_MI325.yaml
2026-03-19 14:30:58 -05:00

13 lines
345 B
YAML

model_name: "deepseek-ai/DeepSeek-V3.2"
accuracy_threshold: 0.95
num_questions: 1319
num_fewshot: 5
startup_max_wait_seconds: 1200
server_args: >-
--enforce-eager
--max-model-len 4096
--tensor-parallel-size 8
--enable-expert-parallel
--attention-backend=TRITON_ATTN
--speculative-config '{"method":"mtp","num_speculative_tokens":3}'