biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI][ROCm] Add gpt-oss w4a8 in CI (#38292)

Browse Source 
Signed-off-by: Bowen Bao <bowenbao@amd.com>
This commit is contained in:
Bowen Bao
2026-04-02 09:06:01 -07:00
committed by GitHub
parent a9b4f07ba2
commit 82a006beeb
2 changed files with 10 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/evals/gpt_oss/configs/gpt-oss-20b-rocm-mxfp4-fp8.yaml Normal file
View File

@@ -0,0 +1,8 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
model_name: amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8
metric_threshold: 0.568
reasoning_effort: low
server_args: "--attention-backend ROCM_AITER_UNIFIED_ATTN"
env:
VLLM_ROCM_USE_AITER: "1"

3
tests/evals/gpt_oss/configs/models-gfx950.txt
View File

@@ -1,3 +1,4 @@
# GFX950 model configurations for GPQA evaluation
# Tests different environment variable combinations
gpt-oss-20b-rocm-baseline.yaml
gpt-oss-20b-rocm-baseline.yaml
gpt-oss-20b-rocm-mxfp4-fp8.yaml