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

[ROCm][CI] Fix ROCm GPT-OSS Eval test group (#36179)

Browse Source 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Andreas Karatzas
2026-03-09 19:55:20 -05:00
committed by GitHub
parent f85b4eda3a
commit 179547d62c
4 changed files with 16 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.buildkite/test-amd.yaml
View File

@@ -1640,7 +1640,7 @@ steps:
- vllm/v1/attention/backends/flashinfer.py - vllm/v1/attention/backends/flashinfer.py
commands: commands:
- uv pip install --system 'gpt-oss[eval]==0.0.5' - uv pip install --system 'gpt-oss[eval]==0.0.5'
- VLLM_ROCM_USE_AITER_MHA=0 VLLM_ROCM_USE_AITER=1 VLLM_USE_AITER_UNIFIED_ATTENTION=1 pytest -s -v tests/evals/gpt_oss/test_gpqa_correctness.py --model openai/gpt-oss-20b --metric 0.58 - pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-gfx942.txt
##### EPLB Accuracy Tests ##### ##### EPLB Accuracy Tests #####
- label: DeepSeek V2-Lite Accuracy - label: DeepSeek V2-Lite Accuracy
@@ -3297,7 +3297,7 @@ steps:
- vllm/v1/attention/backends/flashinfer.py - vllm/v1/attention/backends/flashinfer.py
commands: commands:
- uv pip install --system 'gpt-oss[eval]==0.0.5' - uv pip install --system 'gpt-oss[eval]==0.0.5'
- VLLM_ROCM_USE_AITER_MHA=0 VLLM_ROCM_USE_AITER=1 VLLM_USE_AITER_UNIFIED_ATTENTION=1 pytest -s -v tests/evals/gpt_oss/test_gpqa_correctness.py --model openai/gpt-oss-20b --metric 0.58 - pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-gfx950.txt
##### EPLB Accuracy Tests ##### ##### EPLB Accuracy Tests #####
- label: DeepSeek V2-Lite Accuracy - label: DeepSeek V2-Lite Accuracy

6
tests/evals/gpt_oss/configs/gpt-oss-20b-rocm-baseline.yaml Normal file
View File

@@ -0,0 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
model_name: openai/gpt-oss-20b
metric_threshold: 0.568
reasoning_effort: low
server_args: "--attention-backend ROCM_AITER_UNIFIED_ATTN"

3
tests/evals/gpt_oss/configs/models-gfx942.txt Normal file
View File

@@ -0,0 +1,3 @@
# GFX942 model configurations for GPQA evaluation
# Tests different environment variable combinations
gpt-oss-20b-rocm-baseline.yaml

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

@@ -0,0 +1,3 @@
# GFX950 model configurations for GPQA evaluation
# Tests different environment variable combinations
gpt-oss-20b-rocm-baseline.yaml