8 lines
362 B
YAML
8 lines
362 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 aiter --tokenizer openai/gpt-oss-20b --tensor-parallel-size 2"
|
|
env:
|
|
VLLM_ROCM_USE_AITER: "1" |