[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
@@ -12,7 +12,7 @@ import pytest
|
||||
import pytest_asyncio
|
||||
import requests
|
||||
|
||||
from tests.utils import ROCM_ENV_OVERRIDES, RemoteOpenAIServer
|
||||
from tests.utils import RemoteOpenAIServer
|
||||
from tests.v1.utils import check_request_balancing
|
||||
from vllm.platforms import current_platform
|
||||
|
||||
@@ -186,7 +186,6 @@ class MultinodeInternalLBServerManager:
|
||||
auto_port=False,
|
||||
env_dict={
|
||||
"VLLM_SERVER_DEV_MODE": "1",
|
||||
**ROCM_ENV_OVERRIDES,
|
||||
current_platform.device_control_env_var: ",".join(
|
||||
str(current_platform.device_id_to_physical_device_id(i))
|
||||
for i in range(r, r + gpus_per_node)
|
||||
@@ -308,7 +307,6 @@ class APIOnlyServerManager:
|
||||
auto_port=False,
|
||||
env_dict={
|
||||
"VLLM_SERVER_DEV_MODE": "1",
|
||||
**ROCM_ENV_OVERRIDES,
|
||||
# No GPUs needed for API-only server
|
||||
},
|
||||
)
|
||||
@@ -329,7 +327,6 @@ class APIOnlyServerManager:
|
||||
engines_server_args,
|
||||
auto_port=False,
|
||||
env_dict={
|
||||
**ROCM_ENV_OVERRIDES,
|
||||
current_platform.device_control_env_var: ",".join(
|
||||
str(current_platform.device_id_to_physical_device_id(i))
|
||||
for i in range(self.dp_size * self.tp_size)
|
||||
|
||||
Reference in New Issue
Block a user