[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:
Kevin H. Luu
2026-07-19 19:21:25 -07:00
committed by GitHub
co-authored by Simon Mo OpenAI Codex OpenAI Codex
parent ace9fda495
commit 1dcbbd9cac
17 changed files with 129 additions and 15 deletions
+2
View File
@@ -67,6 +67,8 @@ def test_models(
if kv_cache_dtype == "fp8_e5m2" and current_platform.is_rocm():
pytest.skip(f"{kv_cache_dtype} is currently not supported on ROCm/HIP.")
if kv_cache_dtype == "fp8_e5m2" and current_platform.is_cuda():
pytest.skip(f"{kv_cache_dtype} is not supported by FLASH_ATTN on CUDA.")
if not (
current_platform.is_xpu()