Files
vllm/tests/evals/gpt_oss/configs/gpt-oss-20b-rocm-quark-mxfp4-bf16-triton.yaml
2026-04-07 10:57:09 +08:00

6 lines
331 B
YAML

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
model_name: amd/gpt-oss-20b-w-mxfp4-a-bf16
metric_threshold: 0.568
reasoning_effort: low
server_args: "--attention-backend ROCM_AITER_UNIFIED_ATTN --moe-backend triton --tokenizer openai/gpt-oss-20b --tensor-parallel-size 2"