|
Revision tags: dev, v36.0.9, v44.0.1, v43.0.2, v36.0.8, v24.0.8, v44.0.0, v43.0.1, v42.0.2, v36.0.7, v24.0.7, v43.0.0, v42.0.1, v41.0.4, v42.0.0, v40.0.4, v36.0.6, v24.0.6, v41.0.3, v41.0.2, v41.0.1, v36.0.5, v40.0.3, v41.0.0, v36.0.4, v39.0.2, v40.0.2, v40.0.1, v40.0.0, v39.0.1, v39.0.0, v38.0.4, v37.0.3, v36.0.3, v24.0.5, v38.0.3, v38.0.2, v38.0.1, v37.0.2, v37.0.1, v37.0.0, v36.0.2, v36.0.1, v36.0.0, v35.0.0, v24.0.4, v33.0.2, v34.0.2 |
|
| #
a7e11500 |
| 27-Jun-2025 |
Rahul <[email protected]> |
wasi-nn: Update WIT (#11041)
* update wit spec, update backends, fix onnx example, add compute function with wit/witx both
* cargo fmt, prtest_full
* clippy lint fix
* prtest:full
* fixed submod
wasi-nn: Update WIT (#11041)
* update wit spec, update backends, fix onnx example, add compute function with wit/witx both
* cargo fmt, prtest_full
* clippy lint fix
* prtest:full
* fixed submodule update
* update vendor-wit.sh
show more ...
|
|
Revision tags: v34.0.1, v33.0.1, v24.0.3, v32.0.1, v34.0.0, v33.0.0 |
|
| #
90ac295e |
| 19-May-2025 |
Alex Crichton <[email protected]> |
Update Wasmtime to the 2024 Rust Edition (#10806)
* Update Wasmtime to the 2024 Rust Edition
Now that our MSRV supports the 2024 edition it's possible to make this switch. This commit moves Wasmtim
Update Wasmtime to the 2024 Rust Edition (#10806)
* Update Wasmtime to the 2024 Rust Edition
Now that our MSRV supports the 2024 edition it's possible to make this switch. This commit moves Wasmtime to the 2024 Edition to keep up-to-date with Rust idioms and access many of the edition features exclusive to the 2024 edition.
prtest:full
* Reformat with the 2024 edition
show more ...
|
|
Revision tags: v32.0.0, v31.0.0, v30.0.2, v30.0.1, v30.0.0, v29.0.1, v29.0.0, v28.0.1, v28.0.0, v27.0.0, v26.0.1, v25.0.3, v24.0.2, v26.0.0, v21.0.2, v22.0.1, v23.0.3, v25.0.2, v24.0.1, v25.0.1, v25.0.0, v24.0.0, v23.0.2 |
|
| #
a0442ea0 |
| 05-Aug-2024 |
Hamir Mahal <[email protected]> |
Enforce `uninlined_format_args` for the workspace (#9065)
* Enforce `uninlined_format_args` for the workspace
* fix: failing `Monolith Checks` job
* fix: formatting
|
|
Revision tags: v23.0.1, v23.0.0 |
|
| #
0f4ae88a |
| 27-Jun-2024 |
Andrew Brown <[email protected]> |
wasi-nn: use resources (#8873)
* wasi-nn: use resources
Recent discussion in the wasi-nn proposal (see [wasi-nn#59], e.g.) has concluded that the right approach for representing wasi-nn "things" (t
wasi-nn: use resources (#8873)
* wasi-nn: use resources
Recent discussion in the wasi-nn proposal (see [wasi-nn#59], e.g.) has concluded that the right approach for representing wasi-nn "things" (tensors, graph, etc.) is with a component model _resource_. This sweeping change brings Wasmtime's implementation in line with that decision.
Initially I had structured this PR to remove all of the WITX-based implementation (#8530). But, after consulting in a Zulip [thread] on what other WASI proposals aim to do, this PR pivoted to support _both_` the WITX-based and WIT-based ABIs (e.g., preview1 era versus preview2, component model era). What is clear is that the WITX-based specification will remain "frozen in time" while the WIT-based implementation moves forward.
What that means for this PR is a "split world" paradigm. In many places, we have to distinguish between the `wit` and `witx` versions of the same thing. This change isn't the end state yet: it's a big step forward towards bringing Wasmtime back in line with the WIT spec but, despite my best efforts, doesn't fully fix all the TODOs left behind over several years of development. I have, however, taken the liberty to refactor and fix various parts as I came across them (e.g., the ONNX backend). I plan to continue working on this in future PRs to figure out a good error paradigm (the current one is too wordy) and device residence.
[wasi-nn#59]: https://github.com/WebAssembly/wasi-nn/pull/59 [thread]: https://bytecodealliance.zulipchat.com/#narrow/stream/219900-wasi/topic/wasi-nn's.20preview1.20vs.20preview2.20timeline
prtest:full
* vet: audit `ort`-related crate updates
* Simplify `WasiNnView`
With @alexcrichton's help, this change removes the `trait WasiNnView` and `struct WasiNnImpl` wrapping that the WIT-based implementation used for accessing the host context. Instead, `WasiNnView` is now a `struct` containing the mutable references it needs to make things work. This unwraps one complex layer of abstraction, though it does have the downside that it complicates CLI code to split borrows of `Host`.
* Temporarily disable WIT check
* Refactor errors to use `trappable_error_type`
This change simplifies the return types of the host implementations of the WIT-based wasi-nn. There is more work to be done with errors, e.g., to catch up with the upstream decision to return errors as resources. But this is better than the previous mess.
show more ...
|
|
Revision tags: v22.0.0 |
|
| #
881191ae |
| 11-Jun-2024 |
jianjunz <[email protected]> |
Enable unit test for wasi-nn WinML backend. (#8442)
This test was disabled because GitHub Actions Windows Server image doesn't have desktop experience included. But it looks like we can have a stand
Enable unit test for wasi-nn WinML backend. (#8442)
This test was disabled because GitHub Actions Windows Server image doesn't have desktop experience included. But it looks like we can have a standalone WinML binary downloaded from ONNX Runtime project.
Wasi-nn WinML backend and ONNX Runtime backend now share the same test code as they accept the same input, and they are expected to produce the same result.
This change also make wasi-nn WinML backend as a default feature.
prtest:full
show more ...
|
|
Revision tags: v21.0.1, v21.0.0, v20.0.2, v20.0.1 |
|
| #
72afd847 |
| 02-May-2024 |
Andrew Brown <[email protected]> |
wasi-nn: factor out common test-program code (#8522)
`wasi-nn`'s test program suite is light at the moment but, in order to expand it, this change factors out some of the common bits that are being
wasi-nn: factor out common test-program code (#8522)
`wasi-nn`'s test program suite is light at the moment but, in order to expand it, this change factors out some of the common bits that are being used in the `test-programs` crate. Since all of the tests perform some kind of image classification, the new `nn` module gains `classify` and `sort_results` functions to help with this exact case.
prtest:full
show more ...
|