[CI] Move compatible 1xL4 jobs to H200 35GB MIG (#43024)
Signed-off-by: Simon Mo <simon@inferact.ai> Co-authored-by: Simon Mo <simon@inferact.ai> Co-authored-by: OpenAI Codex <noreply@openai.com> Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
co-authored by
Simon Mo
OpenAI Codex
OpenAI Codex
parent
ace9fda495
commit
1dcbbd9cac
@@ -93,6 +93,9 @@ def test_online_quantization(
|
||||
use_rocm_aiter: bool,
|
||||
monkeypatch,
|
||||
) -> None:
|
||||
if kv_cache_dtype == "fp8" and current_platform.is_device_capability_family(90):
|
||||
pytest.skip("FA3 currently rejects FP8 KV cache output dtype on SM90")
|
||||
|
||||
if use_rocm_aiter:
|
||||
monkeypatch.setenv("VLLM_ROCM_USE_AITER", "1")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user