You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
fix(qwen3.8): satisfy repository contracts and formatting
Community CPU failed on the previous head. Three unrelated causes.
clang-format rejected three sites introduced by the review fixes: a boolean
chain in Qwen38KvCache::ok(), the POSIX headers added to plugin_helpers.cpp for
the kernel staging change, and the open() call in that same function. The C++
sources are now formatted with the version CI runs.
The HF reference sidecar carried the bare term "qwen" in a comment naming this
module's own dotted import path. That term is reserved to the qwen_vl family by
test_hf_transformers_model_plugins_do_not_name_sibling_families, and the qwen3_5
sidecar contains no occurrence of it either. The comment now refers to the
module without naming the path.
Adding a family shifts repository-wide counters that several contract tests
assert exactly. All of them are bumped by one for qwen3_8 and its qwen38-27b
profile, relative to the current main:
test_family_specialization families 85 -> 86
test_trtmc_validate catalog models / ready models 117 -> 118
validation bindings 118 -> 119
dataset-backed binding models 117 -> 118
test_perf_matrix release suite cases 110 -> 111
release raw entries 80 -> 81
family/operation pairs 80 -> 81
distinct families 78 -> 79
public_pipeline_call_wall 85 -> 86
consolidated result rows 110 -> 111
test_repository_contracts delegates to the validate and perf-matrix checks, so
it passes once those counts are correct.
These counters were stale from the first commit of this branch, not from the
review fixes. The earlier local runs covered only four test files and none of
these; the full set now passes.
Validation on one NVIDIA SM 10.0 device with TensorRT 11.1.0.106:
clang-format --dry-run --Werror is clean over every qwen3_8 C++ source; ruff,
tools/legal_headers.py and tools/check_doc_file_references.py are clean; the
eight contract and family test files plus the qwen3_5 regression pass 663/663;
and ctest -R qwen3_8 passes 3/3.
Signed-off-by: Zhenshan Xie <zhenshanx@nvidia.com>
0 commit comments