[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:
Micah Williamson
2026-06-19 15:20:06 -05:00
committed by GitHub
parent ca7e1f2c43
commit 4a083cc858
2 changed files with 5 additions and 2 deletions
+1
View File
@@ -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)