Stream: git-wasmtime

Topic: wasmtime / PR #13892 [wasi-nn] Update openvino-rs

view this post on Zulip Wasmtime GitHub notifications bot (Jul 16 2026 at 23:58):

rahulchaphalkar opened PR #13892 from rahulchaphalkar:fix-windows-ci to bytecodealliance:main:

Updates openvino-rs to 0.11.0 i.e. openvino native updated to 2026.1.2

I have been trying to repro some wasi-nn CI failures on windows runners with error Illegal Instruction, and I believe updating Openvino dependency is possibly a good way to address that.
Its tricky to root cause this, as but I have been running isolated runs of openvino tests and winml tests on windows-2025 runners (in my fork) but haven't hit it yet. (The original failing winml tests ran both openvino and winml).

In short, OneDNN which is a dependency of openvino uses JIT to generate some code, checking the underlying CPU capabilities. This is one of the strongest possibilities for ISA mismatch on a github runner. Updating openvino also updates OneDNN from 3.6.2 to 3.10.2. I see a couple of fixes during that timeframe in OneDNN for illegal instructions, [1], [2]

If we still see these failures after this patch (and I have not been to repro it in my fork till then) then I can introduce additional logging and/or separation of threads/jobs for winml and openvino to identify it.

@alexcrichton this should fail cargo-vet test

view this post on Zulip Wasmtime GitHub notifications bot (Jul 16 2026 at 23:58):

rahulchaphalkar requested pchickey for a review on PR #13892.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 16 2026 at 23:58):

rahulchaphalkar requested wasmtime-wasi-reviewers for a review on PR #13892.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 16 2026 at 23:58):

rahulchaphalkar requested alexcrichton for a review on PR #13892.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 16 2026 at 23:58):

rahulchaphalkar requested wasmtime-default-reviewers for a review on PR #13892.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 17 2026 at 14:34):

alexcrichton updated PR #13892.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 17 2026 at 14:34):

alexcrichton has enabled auto merge for PR #13892.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 17 2026 at 14:34):

:thumbs_up: alexcrichton submitted PR review:

Thanks!

view this post on Zulip Wasmtime GitHub notifications bot (Jul 17 2026 at 14:57):

alexcrichton added PR #13892 [wasi-nn] Update openvino-rs to the merge queue.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 17 2026 at 15:22):

github-merge-queue[bot] removed PR #13892 [wasi-nn] Update openvino-rs from the merge queue.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 17 2026 at 15:25):

alexcrichton commented on PR #13892:

I suppose that (regrettably) answers that :(

view this post on Zulip Wasmtime GitHub notifications bot (Jul 21 2026 at 17:14):

rahulchaphalkar commented on PR #13892:

@alexcrichton Can we merge this?

view this post on Zulip Wasmtime GitHub notifications bot (Jul 21 2026 at 17:22):

alexcrichton commented on PR #13892:

I can re-queue, but the last failure segfaulted the same as before, so I don't think that this resolves the underlying issue

view this post on Zulip Wasmtime GitHub notifications bot (Jul 21 2026 at 17:31):

rahulchaphalkar commented on PR #13892:

I don't see failures for this PR? I saw some of the newer seg fault failures you have linked in the other issues, and they come from various backend tests enabling onnx, winml, and openvino, so its actually more likely its coming from openvino, as that is the common backend being run by default every time along with other tests. This patch hopefully addresses that.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 21 2026 at 17:56):

alexcrichton commented on PR #13892:

The failure is in this event and you have to hit "Show Details" next to it. It's the CI run from being in the merge queue, not the CI run from the PR itself here.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 21 2026 at 20:18):

rahulchaphalkar commented on PR #13892:

Ah, thanks @alexcrichton , didn't realize the failure was in the merge queue.
I dug deeper into this, and believe I finally have the root cause. It is indeed OneDNN (from openvino) as hypothesized in the PR. I managed to capture a couple of failures in my private fork with more logs.
Whenever a INTEL(R) XEON(R) PLATINUM 8573C or similar Emerald Rapids CPU is assigned, OneDNN rightfully assumes bf16 is supported, and dispatches bf16 kernels, and these seem to have a problem actually executing.
E.g. 

onednn_verbose,v1,primitive,exec,cpu,reorder,jit:uni,undef,src:bf16::blocked:abcd::f0 dst:bf16::blocked:acdb::f0,,,1x3x224x224,0.1788

I will file an issue in OneDNN. In the meantime, to stop these CI failures, I tried limiting openvino/onednn to AVX2 on windows CI and that seems to work (kind of tricky to verify since I have to keep rerunning jobs until the right CPU is assigned to that runner).

Do you want me to push that patch here to stop the CI failures, and then work on limiting ISA from within wasmtime, would you rather we do both together? (And then later removing these limitations once OneDNN issue has been resolved).

view this post on Zulip Wasmtime GitHub notifications bot (Jul 21 2026 at 21:40):

alexcrichton commented on PR #13892:

Doing both together sounds reasonable to me, and thanks for the help for tracking this down!

view this post on Zulip Wasmtime GitHub notifications bot (Jul 27 2026 at 20:18):

alexcrichton commented on PR #13892:

As a heads up I'm (temporarily) disabling gating on wasi-nn tests in https://github.com/bytecodealliance/wasmtime/pull/14000

view this post on Zulip Wasmtime GitHub notifications bot (Jul 27 2026 at 22:49):

rahulchaphalkar commented on PR #13892:

The recent failure in merge queue was caused because native openvino wasn't actually updated even though I updated openvino-rs in wasmtime. This patch https://github.com/abrown/install-openvino-action/pull/35 should enable pulling newer openvino, and hopefully fixed things up, as right now the failure has been reproduced only in openvino 2025.1 .

view this post on Zulip Wasmtime GitHub notifications bot (Jul 28 2026 at 14:28):

alexcrichton commented on PR #13892:

Should this also update .github/workflows/main.yml with the new openvino-action tag?

view this post on Zulip Wasmtime GitHub notifications bot (Jul 28 2026 at 16:47):

rahulchaphalkar updated PR #13892.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 28 2026 at 17:08):

rahulchaphalkar commented on PR #13892:

Yes, I've updated that tag now, and its pulling in openvino 2026.1

view this post on Zulip Wasmtime GitHub notifications bot (Jul 28 2026 at 17:13):

alexcrichton added PR #13892 [wasi-nn] Update openvino-rs to the merge queue.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 28 2026 at 17:51):

:check: alexcrichton merged PR #13892.

view this post on Zulip Wasmtime GitHub notifications bot (Jul 28 2026 at 17:51):

alexcrichton removed PR #13892 [wasi-nn] Update openvino-rs from the merge queue.

Last updated: Jul 29 2026 at 05:03 UTC