[MoE Refactor] FusedMoE/MoERunner inversion refactor (#41184)
Signed-off-by: Bill Nell <bnell@redhat.com>
This commit is contained in:
@@ -130,7 +130,7 @@ def test_gpt_oss_lora_tp2(
|
||||
gpu_memory_utilization=0.8,
|
||||
fully_sharded_loras=fully_sharded_loras,
|
||||
enable_expert_parallel=not fully_sharded_loras,
|
||||
compilation_config=vllm.config.CompilationConfig( # Avoid OOM
|
||||
compilation_config=vllm.config.CompilationConfig(
|
||||
cudagraph_specialize_lora=False,
|
||||
),
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user