Unverified Commit aeaf45f5 authored by Hongkuan Zhou's avatar Hongkuan Zhou Committed by GitHub
Browse files

test: update unsupported model name after AIC increase coverage (#7161)


Signed-off-by: default avatarhongkuanz <hongkuanz@nvidia.com>
parent 09c09909
...@@ -4,7 +4,7 @@ ...@@ -4,7 +4,7 @@
# Case 5b: AIC unsupported model, rapid, with planner + throughput scaling # Case 5b: AIC unsupported model, rapid, with planner + throughput scaling
# This should FAIL with a ValueError because throughput-based planner # This should FAIL with a ValueError because throughput-based planner
# requires AIC support. # requires AIC support.
model: "Qwen/Qwen3-32B" model: "meta-llama/Llama-3.1-8B"
backend: vllm backend: vllm
image: "nvcr.io/nvidia/ai-dynamo/dynamo-frontend:latest" image: "nvcr.io/nvidia/ai-dynamo/dynamo-frontend:latest"
hardware: hardware:
......
...@@ -155,7 +155,7 @@ class TestRapidSupported: ...@@ -155,7 +155,7 @@ class TestRapidSupported:
class TestRapidUnsupported: class TestRapidUnsupported:
"""Rapid strategy with AIC-unsupported model (Qwen3-32B on l40s/vllm).""" """Rapid strategy with AIC-unsupported model/hardware combos."""
@pytest.mark.pre_merge @pytest.mark.pre_merge
@pytest.mark.gpu_0 @pytest.mark.gpu_0
...@@ -178,7 +178,6 @@ class TestRapidUnsupported: ...@@ -178,7 +178,6 @@ class TestRapidUnsupported:
ops = _make_ops(tmp_path) ops = _make_ops(tmp_path)
asyncio.run(run_profile(dgdr, ops)) asyncio.run(run_profile(dgdr, ops))
@pytest.mark.skip(reason="Fails with latest AIC - OPS-3852")
@pytest.mark.pre_merge @pytest.mark.pre_merge
@pytest.mark.gpu_0 @pytest.mark.gpu_0
def test_planner_throughput_scaling_raises(self, tmp_path): def test_planner_throughput_scaling_raises(self, tmp_path):
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment