Clarify finite/infinite classification at numerical tolerance boundaries
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 35/100
- Issue type
- Bug
- Clarity
- Mostly clear
- Activity status
- Active
- Tech stack
- javascript
- Domain
- testing
Research direction
Start with assert_array_approx_equals_ulp in webnn/resources/utils.js, which loads alongside testharness.js, and trace how it measures ULP distance between finite maximums and infinities for float16 and float32. Run the four assertions quoted in the issue to confirm they pass. The open question is the intended contract, so a newcomer should first ask maintainers whether finite/infinite/NaN classification should be checked before tolerance. Done means an agreed contract plus regression helper tests covering both signs and directions.
Written by the indexing model from the issue text.
Description
While qualifying language models (tinystories, Mamba, SmolLM2) across Apple devices (multiple generations of iPhone, Apple Watch, Apple TV, and iPad), I found a test-oracle boundary that might be worth clarifying: WPT’s ULP helper considers maximum finite and same-sign infinity one ULP apart.
With testharness.js and webnn/resources/utils.js loaded, all four assertions currently pass:
assert_array_approx_equals_ulp([0x7bff], [Infinity], 1, 'float16');
assert_array_approx_equals_ulp([0x7c00], [65504], 1, 'float16');
assert_array_approx_equals_ulp([3.4028234663852886e38], [Infinity], 1, 'float32');
assert_array_approx_equals_ulp([Infinity], [3.4028234663852886e38], 1, 'float32');
Could we require matching finite/infinite/NaN classification before applying numerical tolerances, after converting the reference to the output dtype? If approximate overflow permits exceptions, those should be explicit in the operation’s error model, right?
Our RustNN strict comparator already tests this as an additional safeguard, and when I searched wider to see if other toolchains/runtimes had run into something similar, I found ONNX Runtime #31761. ONNX fixed a related finite-versus-infinite comparator problem. I'm not saying it always makes sense to pull in ONNX problems/solutions, but it seemed close to me in this case.
If the intended contract is agreed, I can contribute WPT helper regressions covering both signs, both directions and adjacent finite controls. Nearly all of which came up in my multi-model work in RustNN when pinning down accuacy/precision problems that compounded in recurrent graphs.
- Dominant language
- Bikeshed
- Stars
- 566
- Forks
- 72
- Avg merge
- 6d 5h
- Merged PRs (30d)
- 1
Getting set up
- No Dockerfile or Docker Compose file
- No pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from webmachinelearning/webnn
-
Difficulty 5/5 Over a week Newbie friendliness 25/100
webmachinelearning/webnn#966 ·
-
Difficulty 5/5 Over a week Newbie friendliness 35/100
webmachinelearning/webnn#965 ·
-
Difficulty 3/5 1-2 days Newbie friendliness 68/100
webmachinelearning/webnn#964 · 1 comment ·
-
Difficulty 5/5 Over a week Newbie friendliness 30/100
webmachinelearning/webnn#963 · 1 comment · 1 reaction ·
-
Difficulty 5/5 Over a week Newbie friendliness 8/100
webmachinelearning/webnn#961 ·
All issues in webmachinelearning/webnn
Similar issues
-
fix(套件): test_bundle 往仓库的 preset/skills 写哨兵，并发跑的 test_installer 拷贝时撞 ENOENT（CI 红）Possibly taken @Miaotofu01 claimed this today. Openneeds-triage
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Miaotofu01/Study-Mate#216 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
diegosouzapw/OmniRoute#17386 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day