[ROCm][CI] Pin test_rocm_compressed_tensors_w8a8 to TRITON_ATTN (#46180)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
This commit is contained in:
@@ -104,6 +104,7 @@ steps:
|
||||
source_file_dependencies:
|
||||
- csrc/quantization/
|
||||
- vllm/model_executor/layers/quantization
|
||||
- vllm/config/
|
||||
- tests/kernels/quantization
|
||||
- tests/kernels/quantization/test_rocm_skinny_gemms.py
|
||||
- vllm/_aiter_ops.py
|
||||
|
||||
@@ -60,8 +60,10 @@ def test_rocm_compressed_tensors_w8a8(
|
||||
vllm_runner, example_prompts, model_path, max_tokens, num_logprobs
|
||||
):
|
||||
dtype = "bfloat16"
|
||||
|
||||
with vllm_runner(model_path, dtype=dtype) as vllm_model:
|
||||
# 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:
|
||||
vllm_model.generate_greedy_logprobs(example_prompts, max_tokens, num_logprobs)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user