[ROCm][CI] Skip Qwen3.5-35B-A3B-MXFP4-AITER-TP2 for non gfx950 (#46109)

Signed-off-by: charlifu <charlifu@amd.com>
This commit is contained in:
Charlie Fu
2026-06-19 17:20:10 -05:00
committed by GitHub
parent 859e4d436b
commit e6cd8913dd
2 changed files with 18 additions and 0 deletions
+9
View File
@@ -101,6 +101,15 @@ steps:
num_devices: 8
commands:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-h200.txt
mirror:
amd:
device: mi300_8
timeout_in_minutes: 180
depends_on:
- image-build-amd
commands:
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-mi3xx.txt
- label: MoE Refactor Integration Test (H100 - TEMPORARY)
key: moe-refactor-integration-test-h100-temporary
@@ -78,7 +78,16 @@ def test_gsm8k_correctness(config_filename):
"Skipping DeepSeek-V3.2 and DeepSeek-R1 on ROCm platforms "
"due to agent pool disk space issues and pod evictions."
)
if current_platform.is_rocm() and (
"Qwen3.5-35B-A3B-MXFP4-AITER-TP2" in config_filename.name
):
from vllm.platforms.rocm import on_gfx950
if not on_gfx950():
pytest.skip(
"Skipping Qwen3.5-35B-A3B-MXFP4-AITER-TP2 on non-GFX950 platforms. "
"The quantization scheme is not supported on non-GFX950 platforms."
)
# Parse server arguments from config (use shlex to handle quoted strings)
server_args_str = eval_config.get("server_args", "")
server_args = shlex.split(server_args_str) if server_args_str else []