[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:
co-authored by
OpenAI Codex
parent
4f2f31b82e
commit
1ab2801dde
@@ -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
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user