Revert "[TPU][Bugfix] fix OOM issue in CI test (#21550)"
This reverts commit 40d86ee412eeeca93e0c37432db6b96829cb64e2.
This commit is contained in:
@ -59,7 +59,7 @@ def test_basic(
|
||||
# actually test chunked prompt
|
||||
max_num_batched_tokens=1024,
|
||||
max_model_len=8192,
|
||||
gpu_memory_utilization=0.95,
|
||||
gpu_memory_utilization=0.7,
|
||||
max_num_seqs=max_num_seqs,
|
||||
tensor_parallel_size=tensor_parallel_size) as vllm_model:
|
||||
vllm_outputs = vllm_model.generate_greedy(example_prompts,
|
||||
|
Reference in New Issue
Block a user