Commit Graph

65 Commits

Author SHA1 Message Date
ea408ab6c0 wasi-nn: add minimum serialization on WASINNContext (#4387)
currently this is not necessary because context (WASINNContext) is
local to instance. (wasm_module_instance_t)

i plan to make a context shared among instances in a cluster when
fixing https://github.com/bytecodealliance/wasm-micro-runtime/issues/4313.
this is a preparation for that direction.

an obvious alternative is to tweak the module instance context APIs
to allow declaring some kind of contexts instance-local. but i feel,
in this particular case, it's more natural to make "wasi-nn handles"
shared among threads within a "process".

note that, spec-wise, how wasi-nn behaves wrt threads is not defined
at all because wasi officially doesn't have threads yet. i suppose, at
this point, that how wasi-nn interacts with wasi-threads is something
we need to define by ourselves, especially when we are using an outdated
wasi-nn version.

with this change, if a thread attempts to access a context while
another thread is using it, we simply make the operation fail with
the "busy" error. this is intended for the mimimum serialization to
avoid problems like crashes/leaks/etc. this is not intended to allow
parallelism or such.

no functional changes are intended at this point yet.

cf.
https://github.com/bytecodealliance/wasm-micro-runtime/issues/4313
https://github.com/bytecodealliance/wasm-micro-runtime/issues/2430
2025-06-20 09:48:55 +08:00
71c07f3e4e deprecate legacy WAMR-specific "wasi_nn" module (#4382)
wasi_nn.h: deprecate legacy "wasi_nn"

cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4326
2025-06-19 14:32:26 +08:00
aa53d648fa wasi-nn: fix tensor_data abi for wasi_ephemeral_nn (#4379)
it's "(list u8)" in the witx definition.

the new definition matches both of our own host definition
(struct tensor_wasm) and wasmtime.

cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4352
2025-06-19 14:18:36 +08:00
a29f3943ef core/iwasm/libraries/wasi-nn/test: use the correct version of keras (#4383) 2025-06-18 19:24:06 +08:00
db7714f0f5 wasi_nn_tensorflowlite.cpp: reject non-fp32 input earlier (#4388)
this backend assumes fp32 here and there.
it's safer to reject unexpected inputs explicitly.
2025-06-18 19:08:57 +08:00
4bf799c3af core/iwasm/libraries/wasi-nn/test/build.sh: add a tip for intel mac (#4389)
i keep forgetting this and had to re-investigate it at least twice.
hopefully this can be helpful for others too.
2025-06-18 19:06:57 +08:00
cba9001749 wasi-nn: don't try to deinit uninitialized backend (#4375)
cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4339
2025-06-17 17:40:53 +08:00
c9b8c16088 wasi_nn_openvino.c: remove pre/postprocessing and layout assumptions (#4361)
as wasi-nn doesn't have these concepts, the best we can do without
risking breaking certain applications here is to pass through tensors
as they are.

this matches wasmtime's behavior.

tested with:

* wasmtime classification-example
  (with this change, this example fails on tensor size mismatch
  instead of implicitly resizing it.)

* license-plate-recognition-barrier-0007, a converted version
  with non-fp32 output. [1]
  (with this change, this model outputs integers as expected.)

[1] cd7ebe313b/models/public/license-plate-recognition-barrier-0007
2025-06-17 13:01:46 +08:00
2f0750a6fe wasi_nn_openvino.c: add a missing buffer overflow check in get_output (#4353)
cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4351
2025-06-17 11:17:00 +08:00
20be1d33fe wasi_ephemeral_nn.h: prefix identfiers to avoid too generic names (#4358) 2025-06-17 11:15:01 +08:00
745da82cd6 wasi_nn_openvino.c: remove broken xml check (#4365)
`xml.buf[xml.size]` check is broken because it accesses past
the end of the buffer.

anyway, openvino doesn't seem to care the NUL termination.
2025-06-17 11:02:36 +08:00
0d001c4c38 wasi-nn: fix backend leak on multiple loads (#4366)
cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4340
2025-06-17 11:01:07 +08:00
5478d267f4 wasi_nn_openvino.c: remove the tensor layout adjustment logic (#4308)
the logic in question seems like an attempt to work around
some application bugs.
my wild guess is that it was for classification-example.
cf. https://github.com/bytecodealliance/wasmtime/issues/10867
2025-06-12 09:34:14 +08:00
3a087c4244 wamr-wasi-extensions: add a cmake package to provide our wasi extension (#4344)
* wasi_ephemeral_nn.h: add a convenience wrapper header
* wamr-wasi-extensions: add a cmake package to provide our wasi extension

the sample app was tested with:
* wasmtime
* iwasm with https://github.com/bytecodealliance/wasm-micro-runtime/pull/4308

currently only contains wasi-nn.
maybe it makes sense to add lib-socket things as well.

cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4288
2025-06-12 09:33:25 +08:00
c932597057 wasi_nn_types.h: remove a seemingly stale comment (#4348) 2025-06-12 09:29:59 +08:00
ea5757f1d7 wasi-nn: do not assign wasi_nn_ctx->backend multiple times (#4329) 2025-06-09 11:36:31 +08:00
4d6b8dcd5d wasi_nn.h: make this compatible with wasi_ephemeral_nn (#4330)
- wasi_nn.h: make this compatible with wasi_ephemeral_nn
cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4323

- fix WASM_ENABLE_WASI_EPHEMERAL_NN build
this structure is used by host logic as well.
ideally definitions for wasm and host should be separated.
until it happens, check __wasm__ to avoid the breakage.
2025-06-09 11:36:05 +08:00
933f8124b0 wasi-nn: fix the size of tensor->type (#4333)
* this enum is (@witx tag u8) in witx
* it seems that some wasm modules actually use non-zero padding
  and cause errors
* it's a bad practice to use C enum for ABI description anyway
2025-06-06 15:08:18 +08:00
769d16eaab wasi-nn: move some host-only things out of wasi_nn_types.h (#4334)
cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4324
2025-06-06 15:07:29 +08:00
79cb4366ae wasi-nn: remove unused wasi_nn_dump_tensor_dimension prototype (#4325) 2025-06-05 09:48:28 +08:00
b20ebc2724 wasi_nn.h: add import_name attribute (#4328)
this would fix undefined symbol errors by making it clear
these functions are imported.

references:
e2c698c7e8/llvm/lib/MC/WasmObjectWriter.cpp (L1798-L1799)
e2c698c7e8/llvm/lib/Object/WasmObjectFile.cpp (L749-L752)
e2c698c7e8/lld/wasm/Symbols.cpp (L203)
e2c698c7e8/lld/wasm/Relocations.cpp (L36-L40)
2025-06-05 09:48:00 +08:00
85efe08431 wasi-nn: protect the backend lookup table with a lock (#4319)
this would avoid potential issues when multiple instances happen to
make an attempt to load a backend at the same time.

Fixes: https://github.com/bytecodealliance/wasm-micro-runtime/issues/4314
2025-06-05 09:19:46 +08:00
6a00874f2f wasi_nn_openvino.c: make this buildable (#4305) 2025-06-03 13:28:13 +08:00
61cb97221e wasi-nn: fix shared library filenames for macOS (#4306)
tested with openvino
2025-06-03 13:23:19 +08:00
ae6e490ad5 fix wasi-nn abi definitions (#4307)
sync with a more appropriate version of the definitions.

as we use the "wasi_ephemeral_nn", which is p1-based, it seems
more appropriate to use definitions from witx, not wit.

it's a bit unfortunate p2-based wasi-nn made gratuitous changes
like this from p1.

note: this is an ABI change.
2025-06-03 13:22:48 +08:00
16c46751ac wasi-nn: remove "backends" argument from detect_and_load_backend() (#4309)
it seems meaningless and quite confusing to access a table with
two aliases ("lookup" and "backends") within a function.

no functional changes are intended.
2025-06-03 13:22:27 +08:00
1c12a32066 wasi_nn_openvino.c: fix a few printf formats (#4310) 2025-06-03 13:21:32 +08:00
aa1ff778b9 add load_by_name in wasi-nn (#4298) 2025-06-03 06:26:58 +08:00
3ab9f84026 Dockerfile.vx-delegate build error fix (#4273)
- specify tensorflow version & bugfix
2025-05-28 20:29:41 +08:00
d085d1ccf7 Keep fix the CMake compatibility issue (#4180)
```
CMake Error at CMakeLists.txt:4 (cmake_minimum_required):
  Compatibility with CMake < 3.5 has been removed from CMake.

  Update the VERSION argument <min> value.  Or, use the <min>...<max> syntax
  to tell CMake that the project requires at least <min> but has been updated
  to work with policies introduced by <max> or earlier.

  Or, add -DCMAKE_POLICY_VERSION_MINIMUM=3.5 to try configuring anyway.
```
2025-04-15 12:51:19 +08:00
2a2632444b Refactor Dockerfile and update .dockerignore for wasi-nn tests; adjust map-dir parameters in smoke test script (#4158) 2025-04-10 11:59:59 +08:00
dde6477fa5 Fix iwasm build error when WAMR_BUILD_WASI_NN enabled
A recent change on ./product-mini/platforms/linux/CMakeLists.txt renamed
libiwasm to vmlib, but wasi-nn.cmake still wants to link libiwasm.so.
Replace libiwasm with vmlib in wasi-nn.cmake to resolve iwasm build error
when WAMR_BUILD_WASI_NN enabled.
2025-03-13 17:08:22 +00:00
412631ac13 fix: correct typos and improve comments across multiple files by codespell (#4116)
Signed-off-by: Huang Qi <huangqi3@xiaomi.com>
2025-03-07 08:21:54 +08:00
b2c7cb2375 Use wasm32-wasip1 instead of wasm32-wasi target for rust code (#4057)
Rust compiler previously deprecated, and now removed the wasm32-wasi target and replaced it with wasm32-wasip1. This
change updates all the occurrences of wasm32-wasi in the context of Rust compilation.

covers the wasi-nn/test.
2025-02-05 11:31:49 +08:00
9598611e35 CMakeLists.txt: Do not require C++ (#3956)
By default, the project() CMake command defaults to C and C++. [1]
Therefore, CMake might perform tests for both C and C++ compilers as
part of the configuration phase.

However, this has the consequence of the configuration phase to fail if
the system does not have a C++ toolchain installed, even if C++ is not
really used by the top-level project under the default settings.

Some configurations might still require a C++ toolchain, so
enable_language is selectively called under such circumstances.

[1]: https://cmake.org/cmake/help/latest/command/project.html
2024-12-20 13:05:50 +08:00
30539bf50c Fix compilation error found in tflite test (#3820)
ps. https://github.com/bytecodealliance/wasm-micro-runtime/pull/3817
2024-10-08 09:54:39 +08:00
0599351262 wasi-nn: Add a new target for llama.cpp as a wasi-nn backend (#3709)
Minimum support:
- [x] accept (WasmEdge) customized model parameters. metadata.
- [x] Target [wasmedge-ggml examples](https://github.com/second-state/WasmEdge-WASINN-examples/tree/master/wasmedge-ggml)
  - [x] basic
  - [x] chatml
  - [x] gemma
  - [x] llama
  - [x] qwen

---

In the future, to support if required:
- [ ] Target [wasmedge-ggml examples](https://github.com/second-state/WasmEdge-WASINN-examples/tree/master/wasmedge-ggml)
  - [ ] command-r. (>70G memory requirement)
  - [ ] embedding. (embedding mode)
  - [ ] grammar. (use the grammar option to constrain the model to generate the JSON output)
  - [ ] llama-stream. (new APIS `compute_single`, `get_output_single`, `fini_single`)
  - [ ] llava. (image representation)
  - [ ] llava-base64-stream. (image representation)
  - [ ] multimodel. (image representation)
- [ ] Target [llamaedge](https://github.com/LlamaEdge/LlamaEdge)
2024-09-10 08:45:18 +08:00
140ff25d46 wasi-nn: Apply new architecture (#3692)
ps.
https://github.com/bytecodealliance/wasm-micro-runtime/issues/3677
2024-08-13 09:14:52 +08:00
0a56abc6d6 build(deps): bump tensorflow in /core/iwasm/libraries/wasi-nn/test (#3675)
Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 2.11.1 to 2.12.1.
- [Release notes](https://github.com/tensorflow/tensorflow/releases)
- [Changelog](https://github.com/tensorflow/tensorflow/blob/master/RELEASE.md)
- [Commits](https://github.com/tensorflow/tensorflow/compare/v2.11.1...v2.12.1)

---
updated-dependencies:
- dependency-name: tensorflow
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-02 09:17:12 +08:00
058bc47102 [wasi-nn] Add a new wasi-nn backend openvino (#3603) 2024-07-22 17:16:41 +08:00
77da87ca51 wasi-nn: Use numpy v1 in wasi-nn test requirements.txt (#3582)
We need to fix numpy version since the latest is incompatible.

> A module that was compiled using NumPy 1.x cannot be run in
NumPy 2.0.0 as it may crash. To support both 1.x and 2.x
versions of NumPy, modules must be compiled with NumPy 2.0.
Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.
2024-07-02 09:39:46 +08:00
d36160b294 wasi-nn: Add wasmedge-wasinn-example as smoke test (#3554) 2024-06-24 12:03:08 +08:00
db025e457a sync up with latest wasi-nn spec (#3530) 2024-06-17 14:58:09 +08:00
f844b33b2d Make wasi-nn backends as separated shared libraries (#3509)
- All files under *core/iwasm/libraries/wasi-nn* are compiled as shared libraries
- *wasi-nn.c* is shared between backends
- Every backend has a separated shared library
- If wasi-nn feature is enabled, iwasm will depend on shared library libiwasm.so
  instead of linking static library libvmlib.a
2024-06-14 12:06:56 +08:00
028f43bc18 Fix compilation warnings of wasi-nn (#3497) 2024-06-07 10:49:44 +08:00
bd44117676 Add wasi-nn example as smoke test case (#3501) 2024-06-07 10:26:09 +08:00
cef88deedb Add wasi_ephemeral_nn module support (#3241)
Add `wasi_ephemeral_nn` module support with optional cmake variable,
which was mentioned in #3229.
2024-03-21 21:05:34 +08:00
0ee5ffce85 Refactor APIs and data structures as preliminary work for Memory64 (#3209)
# Change the data type representing linear memory address from u32 to u64

## APIs signature changes
- (Export)wasm_runtime_module_malloc
  - wasm_module_malloc
    - wasm_module_malloc_internal
  - aot_module_malloc
    - aot_module_malloc_internal
- wasm_runtime_module_realloc
  - wasm_module_realloc
    - wasm_module_realloc_internal
  - aot_module_realloc
    - aot_module_realloc_internal
- (Export)wasm_runtime_module_free
  - wasm_module_free
    - wasm_module_free_internal
  - aot_module_malloc
    - aot_module_free_internal
- (Export)wasm_runtime_module_dup_data
  - wasm_module_dup_data
  - aot_module_dup_data
- (Export)wasm_runtime_validate_app_addr
- (Export)wasm_runtime_validate_app_str_addr
- (Export)wasm_runtime_validate_native_addr
- (Export)wasm_runtime_addr_app_to_native
- (Export)wasm_runtime_addr_native_to_app
- (Export)wasm_runtime_get_app_addr_range
- aot_set_aux_stack
- aot_get_aux_stack
- wasm_set_aux_stack
- wasm_get_aux_stack
- aot_check_app_addr_and_convert, wasm_check_app_addr_and_convert
  and jit_check_app_addr_and_convert
- wasm_exec_env_set_aux_stack
- wasm_exec_env_get_aux_stack
- wasm_cluster_create_thread
- wasm_cluster_allocate_aux_stack
- wasm_cluster_free_aux_stack

## Data structure changes
- WASMModule and AOTModule
  - field aux_data_end, aux_heap_base and aux_stack_bottom
- WASMExecEnv
  - field aux_stack_boundary and aux_stack_bottom
- AOTCompData
  - field aux_data_end, aux_heap_base and aux_stack_bottom
- WASMMemoryInstance(AOTMemoryInstance)
  - field memory_data_size and change __padding to is_memory64
- WASMModuleInstMemConsumption
  - field total_size and memories_size
- WASMDebugExecutionMemory
  - field start_offset and current_pos
- WASMCluster
  - field stack_tops

## Components that are affected by the APIs and data structure changes
- libc-builtin
- libc-emcc
- libc-uvwasi
- libc-wasi
- Python and Go Language Embedding
- Interpreter Debug engine
- Multi-thread: lib-pthread, wasi-threads and thread manager
2024-03-12 11:38:50 +08:00
1a88104160 Remove module instance from hashmap in wasi_nn_destroy (#2613)
When destroying wasi-nn context, module instance should be also
removed from hashmap to avoid memory leak.
2023-10-03 08:33:11 +08:00
b45d014112 wasi-nn: Improve TPU support (#2447)
1. Allow TPU and GPU support at the same time.
2. Add Dockerfile to run example with [Coral USB](https://coral.ai/products/accelerator/).
2023-08-14 20:03:56 +08:00