Files
vllm/tests/evals/gsm8k/configs/moe-refactor/Mixtral-8x7B-Fp8-AutoFp8-triton.yaml

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

6 lines
189 B
YAML
Raw Normal View History

model_name: "amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV"
accuracy_threshold: 0.62
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"