[ROCm] Fix OOB During Model Warmup With ROCM_ATTN and MRV2 (#46548)
Signed-off-by: Micah Williamson <micah.williamson@amd.com> Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com> Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
This commit is contained in:
co-authored by
Matthew Wong
parent
1cd3e0e945
commit
b3a688cb9e
@@ -60,10 +60,8 @@ def test_rocm_compressed_tensors_w8a8(
|
||||
vllm_runner, example_prompts, model_path, max_tokens, num_logprobs
|
||||
):
|
||||
dtype = "bfloat16"
|
||||
# Pin to TRITON_ATTN, see https://github.com/vllm-project/vllm/issues/46179
|
||||
with vllm_runner(
|
||||
model_path, dtype=dtype, attention_backend="TRITON_ATTN"
|
||||
) as vllm_model:
|
||||
|
||||
with vllm_runner(model_path, dtype=dtype) as vllm_model:
|
||||
vllm_model.generate_greedy_logprobs(example_prompts, max_tokens, num_logprobs)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user