[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907)

Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
Andreas Karatzas
2026-08-11 14:19:16 -04:00
committed by GitHub
co-authored by OpenAI Codex
parent 4f2f31b82e
commit 1ab2801dde
56 changed files with 500 additions and 558 deletions
@@ -10,7 +10,7 @@ import pytest
import pytest_asyncio
# downloading lora to test lora requests
from tests.utils import ROCM_ENV_OVERRIDES, ROCM_EXTRA_ARGS, RemoteOpenAIServer
from tests.utils import ROCM_EXTRA_ARGS, RemoteOpenAIServer
# any model with a chat template should work here
MODEL_NAME = "Qwen/Qwen3-0.6B"
@@ -144,9 +144,7 @@ def server():
"--enforce-eager",
] + ROCM_EXTRA_ARGS
with RemoteOpenAIServer(
MODEL_NAME, args, env_dict=ROCM_ENV_OVERRIDES
) as remote_server:
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
yield remote_server