debug-trt-mismatch
Skill290 starsChanged 45 days agoApache-2.0View on GitHub
Diagnose a TensorRT-Model-Connect family whose native output disagrees with its declared reference or family-owned correctness contract.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- website/static/llms.txtllms.txt
- doc-syncSkill
- fp16-trt-networkSkill
- optimize-model-precisionSkill
- pr-babysitterSkill
- profile-modelSkill
- review-trtmc-prSkill
- setup-trtmc-environmentSkill
- submit-github-bug-issueSkill
- submit-github-prSkill
- transform-modelSkill
- write-git-messagesSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 47
Never weaken a correctness gate to make the mismatch disappear.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Debug a TensorRT Mismatch
Find the first family-owned boundary that diverges without changing the workload or acceptance rule.
Start from the owning case
Record the repository revision, checkpoint revision, family testcase, build inputs, runtime root, hardware, seed, and request. Read these files before changing code:
families/<family>/tests/manifests/<case>.jsonfamilies/<family>/tests/thresholds/<case>.jsonfamilies/<family>/tests/test_e2e.py
Reproduce the exact direct E2E path:
PYTHONPATH=core/builder:apps/benchmark:. python3 -m pytest \
families/<family>/tests/test_e2e.py \
--e2e-testcase <case> -vvProvide the testcase's required TRTMC_BINARY, TRTMC_RUNTIME_ROOT, local
checkpoint, and GPU environment. Do not replace its reference, seed, or
threshold with a smaller smoke test.
Localize inside the family
Separate build, native execution, reference execution, and comparison. Then narrow the first failing boundary in the owning family: inputs and preprocessing, weight mapping, graph output, runtime bindings or state, postprocessing, or the family contract.
Reuse an existing family-local probe or test when one exists. Add a focused family-local diagnostic only when the current evidence cannot identify the boundary. Do not move model policy into core or import another family to share debug code.
Never weaken a correctness gate to make the mismatch disappear. If the gate is suspected to be wrong, demonstrate that independently and request review.
Report the exact reproducer, first divergent boundary, evidence that ruled out earlier stages, smallest owner-local fix, and checks still not run.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

