en Copyright 2015 Java http://172.16.0.5:8080/history/wasmtime-44.0.1/crates/test-programs/src/bin/nn_wit_image_classification_winml_named.rs#a7e11500 wasi-nn: Update WIT (#11041)* update wit spec, update backends, fix onnx example, add compute functionwith wit/witx both* cargo fmt, prtest_full* clippy lint fix* prtest:full* fixed submodule update* update vendor-wit.sh List of files: /wasmtime-44.0.1/crates/test-programs/src/bin/nn_wit_image_classification_winml_named.rs Fri, 27 Jun 2025 18:53:14 +0000 Rahul <rahul.s.chaphalkar@intel.com> http://172.16.0.5:8080/history/wasmtime-44.0.1/crates/test-programs/src/bin/nn_wit_image_classification_winml_named.rs#a0442ea0 Enforce `uninlined_format_args` for the workspace (#9065)* Enforce `uninlined_format_args` for the workspace* fix: failing `Monolith Checks` job* fix: formatting List of files: /wasmtime-44.0.1/crates/test-programs/src/bin/nn_wit_image_classification_winml_named.rs Mon, 05 Aug 2024 09:59:59 +0000 Hamir Mahal <hamirmahal@gmail.com> http://172.16.0.5:8080/history/wasmtime-44.0.1/crates/test-programs/src/bin/nn_wit_image_classification_winml_named.rs#0f4ae88a wasi-nn: use resources (#8873)* wasi-nn: use resourcesRecent discussion in the wasi-nn proposal (see [wasi-nn#59], e.g.) hasconcluded that the right approach for representing wasi-nn "things"(tensors, graph, etc.) is with a component model _resource_. Thissweeping change brings Wasmtime's implementation in line with thatdecision.Initially I had structured this PR to remove all of the WITX-basedimplementation (#8530). But, after consulting in a Zulip [thread] onwhat 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 specificationwill remain "frozen in time" while the WIT-based implementation movesforward.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 samething. This change isn't the end state yet: it's a big step forwardtowards bringing Wasmtime back in line with the WIT spec but, despite mybest efforts, doesn't fully fix all the TODOs left behind over severalyears of development. I have, however, taken the liberty to refactor andfix various parts as I came across them (e.g., the ONNX backend). I planto continue working on this in future PRs to figure out a good errorparadigm (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.20preview2.20timelineprtest: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 usedfor accessing the host context. Instead, `WasiNnView` is now a `struct`containing the mutable references it needs to make things work. Thisunwraps one complex layer of abstraction, though it does have thedownside 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 ofthe 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. List of files: /wasmtime-44.0.1/crates/test-programs/src/bin/nn_wit_image_classification_winml_named.rs Thu, 27 Jun 2024 19:14:03 +0000 Andrew Brown <andrew.brown@intel.com>