[CI][AMD] Bump torchao to v18 for Python 3.14 (#53009)
Signed-off-by: Ryan Rock <ryan.rock@amd.com> Co-authored-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
co-authored by
Andreas Karatzas
parent
6af44e2887
commit
59e6682c21
@@ -2540,7 +2540,7 @@ steps:
|
||||
# we can only upgrade after this is resolved
|
||||
# TODO(jerryzh168): resolve the above comment
|
||||
- unset VLLM_USE_V2_MODEL_RUNNER
|
||||
- uv pip install --system torchao==0.17.0
|
||||
- uv pip install --system torchao==0.18.0
|
||||
- uv pip install --system conch-triton-kernels
|
||||
- VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
|
||||
- if [ "$$BUILDKITE_PARALLEL_JOB" = "0" ]; then pytest -v -s rocm/test_moe_weight_replay.py; fi
|
||||
|
||||
Reference in New Issue
Block a user