Add "load_by_name" API at wasi-nn by HongxiaWangSSSS · Pull Request #4267 · bytecodealliance/wasm-micro-runtime

HongxiaWangSSSS · 2025-05-12T03:10:38Z

When using WASI-NN ,we want to reduce copying the AI model from the host to the WASM by using "load_by_name" API.
We also want to use it to improve the performance, keep the safety and WASI-NN also supports this method on different backends.

I test with 3 tflite models.(x86_64, Ubuntu 22.04)

Both coco_ssd_mobilenet_v1 and coco_ssd_mobilenet_v3 are for detection, its file size and input tensor size is different.
mobilenet_v2 is for classification and size is more bigger.

The time consumed does not show a linear growth as the file size increases.
For most cases, load_by_name will more faster whether the load tflite or the entire inference process (load+ set input +compute +get output).

…y_name

yamt · 2025-05-12T10:03:27Z


 wasi_nn_error
-load_by_name(const char *name, graph *g)
+load_by_name(char *name, uint32_t name_len, graph *g)


is this a bug fix?

wasi_nn.h is a header for WebAssembly applications written in the C language. Is there a specific reason that we need to change it?

yes, its a bugfix,

Since we have two sets of APIs for historical reasons, we might remove one in another PR. For now, let's ensure both are functional.

I suggest we use WASM_ENABLE_WASI_EPHEMERAL_NN on the wasm side.

With this flag, we declare two sets of APIs in wasi_nn.h. Please align with the content of native_symbols_wasi_nn in wasi_nn.c

@lum1n0us
Where can I find the function prototypes for wasi_ephemeral_nn?
For functions like get_output, the signatures are different, so simply replacing wasi_nn with wasi_ephemeral_nn mechanically doesn't seem to work.

wasm-micro-runtime/core/iwasm/libraries/wasi-nn/src/wasi_nn.c

Lines 690 to 704 in c018b8a

#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0

REG_NATIVE_FUNC(load, "(*iii*)i"),

REG_NATIVE_FUNC(load_by_name, "(*i*)i"),

REG_NATIVE_FUNC(load_by_name_with_config, "(*i*i*)i"),

REG_NATIVE_FUNC(init_execution_context, "(i*)i"),

REG_NATIVE_FUNC(set_input, "(ii*)i"),

REG_NATIVE_FUNC(compute, "(i)i"),

REG_NATIVE_FUNC(get_output, "(ii*i*)i"),

#else /* WASM_ENABLE_WASI_EPHEMERAL_NN == 0 */

REG_NATIVE_FUNC(load, "(*ii*)i"),

REG_NATIVE_FUNC(init_execution_context, "(i*)i"),

REG_NATIVE_FUNC(set_input, "(ii*)i"),

REG_NATIVE_FUNC(compute, "(i)i"),

REG_NATIVE_FUNC(get_output, "(ii**)i"),

#endif /* WASM_ENABLE_WASI_EPHEMERAL_NN != 0 */

Even when referring to the wasi-nn specification, the signatures declared there don’t appear to match what is used for wasi_ephemeral_nn
https://github.com/WebAssembly/wasi-nn/blob/71320d95b8c6d43f9af7f44e18b1839db85d89b4/wasi-nn.witx#L59-L86

@HongxiaWangSSSS I suggest we use WASM_ENABLE_WASI_EPHEMERAL_NN on the wasm side and there will be two sets for wasi_ephemeral_nn and wasi_nn. wasi_nn will be deprecated in the future.

#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0 wasi_nn_error load(graph_builder_array *builder, graph_encoding encoding, execution_target target, graph *g) __attribute__((import_module("wasi_ephemeral_nn"))); wasi_nn_error load_by_name(const char *name, uint32_t len, graph *g) __attribute__((import_module("wasi_ephemeral_nn"))); wasi_nn_error load_by_name_with_config(const char *name, uint32_t name_len, void *config, uint32_t config_len, graph *g) __attribute__((import_module("wasi_ephemeral_nn")));; wasi_nn_error init_execution_context(graph g, graph_execution_context *exec_ctx) __attribute__((import_module("wasi_ephemeral_nn")));; wasi_nn_error set_input(graph_execution_context ctx, uint32_t index, tensor *tensor) __attribute__((import_module("wasi_ephemeral_nn")));; wasi_nn_error compute(graph_execution_context ctx) __attribute__((import_module("wasi_ephemeral_nn")));; wasi_nn_error get_output(graph_execution_context ctx, uint32_t index, tensor_data output_tensor, uint32_t *output_tensor_size) __attribute__((import_module("wasi_ephemeral_nn")));; #else wasi_nn_error load(graph_builder_array *builder, graph_encoding encoding, execution_target target, graph *g) __attribute__((import_module("wasi_nn"))); wasi_nn_error init_execution_context(graph g, graph_execution_context *ctx) __attribute__((import_module("wasi_nn"))); wasi_nn_error set_input(graph_execution_context ctx, uint32_t index, tensor *tensor) __attribute__((import_module("wasi_nn"))); wasi_nn_error compute(graph_execution_context ctx) __attribute__((import_module("wasi_nn"))); wasi_nn_error get_output(graph_execution_context ctx, uint32_t index, tensor_data output_tensor, uint32_t *output_tensor_size) __attribute__((import_module("wasi_nn"))); #endif

Is there a mismatch in the function signature?

wasm-micro-runtime/core/iwasm/libraries/wasi-nn/src/wasi_nn.c

Line 697 in c018b8a

REG_NATIVE_FUNC(get_output, "(ii*i*)i"),

and

wasi_nn_error
get_output(graph_execution_context ctx, uint32_t index,
tensor_data output_tensor, uint32_t *output_tensor_size) attribute((import_module("wasi_ephemeral_nn")));

YES. there should be two versions, one for wasi_ephemeral_nn, another for wasi_nn. please refer to:

#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0 wasi_nn_error wasi_nn_load(wasm_exec_env_t exec_env, graph_builder_wasm *builder, uint32_t builder_wasm_size, graph_encoding encoding, execution_target target, graph *g) #else /* WASM_ENABLE_WASI_EPHEMERAL_NN == 0 */ wasi_nn_error wasi_nn_load(wasm_exec_env_t exec_env, graph_builder_array_wasm *builder, graph_encoding encoding, execution_target target, graph *g) #endif /* WASM_ENABLE_WASI_EPHEMERAL_NN != 0 */ #if WASM_ENABLE_WASI_EPHEMERAL_NN != 0 wasi_nn_error wasi_nn_get_output(wasm_exec_env_t exec_env, graph_execution_context ctx, uint32_t index, tensor_data output_tensor, uint32_t output_tensor_len, uint32_t *output_tensor_size) #else /* WASM_ENABLE_WASI_EPHEMERAL_NN == 0 */ wasi_nn_error wasi_nn_get_output(wasm_exec_env_t exec_env, graph_execution_context ctx, uint32_t index, tensor_data output_tensor, uint32_t *output_tensor_size) #endif /* WASM_ENABLE_WASI_EPHEMERAL_NN != 0 */

If so, we need to define it at wasi_nn.h

wasi_nn_error get_output(graph_execution_context ctx, uint32_t index, tensor_data output_tensor, uint32_t output_tensor_len, uint32_t *output_tensor_size) __attribute__((import_module("wasi_ephemeral_nn")));

But the backend definition doesn't look like it matches (signature might be ok)

wasm-micro-runtime/core/iwasm/libraries/wasi-nn/src/wasi_nn_tensorflowlite.cpp

Lines 366 to 368 in c018b8a

__attribute__((visibility("default"))) wasi_nn_error

get_output(void *tflite_ctx, graph_execution_context ctx, uint32_t index,

tensor_data output_tensor, uint32_t *output_tensor_size)

Yes. I am suggestion this #4267 (comment) as the new content of wasi_nn.h. Plus, #4267 (comment).

lum1n0us · 2025-05-12T12:34:26Z

    REG_NATIVE_FUNC(get_output, "(ii*i*)i"),
 #else  /* WASM_ENABLE_WASI_EPHEMERAL_NN == 0 */
    REG_NATIVE_FUNC(load, "(*ii*)i"),
+    REG_NATIVE_FUNC(load_by_name, "(*i*)i"),


Why not use -DWASM_ENABLE_WASI_EPHEMERAL_NN=1?

at first, i just built with -DWASM_ENABLE_WASI_NN=1.

If use -DWAMR_BUILD_WASI_EPHEMERAL_NN=1 during compilation, you will be able to use the set of APIs, including load_by_name(). There is no need to change this line.

If -DWAMR_BUILD_WASI_EPHEMERAL_NN=1 must be added , I think there is no need to add this line.
Currently, it is possible to use the default wasi-nn instead of wasi_ephemeral_nn.

Yes. Please do it.

So, does that mean that the ephemeral version is meant to be compatible with Rust (especially WasmEdge), whereas the non-ephemeral one doesn't need to be?
If that's the case, wouldn't it make sense to add load_by_name to the wasi_nn.h header, which is a straightforward C interpretation of the witx specification?

Yes. load_by_name() needs a new signature.

Eventually, load_by_name() and wasm_load_by_name() should only exist when WASM_ENABLE_WASI_EPHEMERAL_NN is set to 1. If you transform wasm with the flag WASM_ENABLE_WASI_EPHEMERAL_NN=1, you will get wasm with import requirements from wasi_ephemeral_nn, which offers better performance.

#4267 (comment)
said this is for C langage, so why not keep it for non-wasi_ephemeral_nn to provide the same performance ?

In my mind, wasi_ephemeral_nn is legacy and should be deprecated. If there are C APIs, they should follow the Rust API's design to avoid unnecessary changes for the runtime.

lum1n0us · 2025-05-12T12:39:53Z


 wasi_nn_error
-load_by_name(const char *name, graph *g)
+load_by_name(char *name, uint32_t name_len, graph *g)


wasi_nn.h is a header for WebAssembly applications written in the C language. Is there a specific reason that we need to change it?

lum1n0us · 2025-05-12T12:40:59Z

    }
-    if (tfl_ctx->models[g].model_pointer == NULL) {
+    if (tfl_ctx->models[g].model_pointer == NULL
+        && tfl_ctx->models[g].model == NULL) {


The original version can output different information based on various invalid argument cases. Is there a specific reason we need to merge them?

If call load_by_name(), there is no need to save the tflite buf to model_pointer.
https://github.com/HongxiaWangSSSS/wasm-micro-runtime/blob/c5414fd28baf973e3c95db1318de4d26f88007d3/core/iwasm/libraries/wasi-nn/src/wasi_nn_tensorflowlite.cpp#L141C49-L141C68

I'm not sure why not free model_point after below operation in load()
https://github.com/HongxiaWangSSSS/wasm-micro-runtime/blob/c5414fd28baf973e3c95db1318de4d26f88007d3/core/iwasm/libraries/wasi-nn/src/wasi_nn_tensorflowlite.cpp#L151

It is required to validate TFLitesContext.models[g] for both cases, using load() and load_by_name(). It will not be acceptable if the change disables one of these cases.

Whether it is load or load_by_name, the check of models[g].model_pointerdoes not seem to be necessary, just make sure the models[g].model is not NULL maybe is enough.
Do you have any idea?

does not seem to be necessary.

Why is that?

after this operation, the models[g].model_pointer's connect has been saved in models[g].model.

https://github.com/tensorflow/tensorflow/blob/02896e880298894beedc71f8666f6949ad0e174f/tensorflow/compiler/mlir/lite/core/model_builder_base.h#L169-#L184

/// Builds a model based on a pre-loaded flatbuffer. /// Caller retains ownership of the buffer and should keep it alive until /// the returned object is destroyed. Caller also retains ownership of /// `error_reporter` and must ensure its lifetime is longer than the /// FlatBufferModelBase instance. /// Returns a nullptr in case of failure. /// NOTE: this does NOT validate the buffer so it should NOT be called on /// invalid/untrusted input. Use VerifyAndBuildFromBuffer in that case static std::unique_ptr<T> BuildFromBuffer( const char* caller_owned_buffer, size_t buffer_size, ErrorReporter* error_reporter = T::GetDefaultErrorReporter()) { error_reporter = ValidateErrorReporter(error_reporter); std::unique_ptr<Allocation> allocation( new MemoryAllocation(caller_owned_buffer, buffer_size, error_reporter)); return BuildFromAllocation(std::move(allocation), error_reporter); }

If I understand correctly, model_pointer acts as a pre-allocated buffer, and its ownership is still held by the caller, in our case, tfl_ctx. Meanwhile, model holds the ownership of the result from tflite::FlatBufferModel::BuildFromBuffer(). Therefore, both are required.

lum1n0us · 2025-05-13T23:36:42Z

    }
-    if (tfl_ctx->models[g].model_pointer == NULL) {
+    if (tfl_ctx->models[g].model_pointer == NULL
+        && tfl_ctx->models[g].model == NULL) {


does not seem to be necessary.

Why is that?

lum1n0us · 2025-05-14T01:02:22Z

    REG_NATIVE_FUNC(get_output, "(ii*i*)i"),
 #else  /* WASM_ENABLE_WASI_EPHEMERAL_NN == 0 */
    REG_NATIVE_FUNC(load, "(*ii*)i"),
+    REG_NATIVE_FUNC(load_by_name, "(*i*)i"),


Yes. Please do it.

lum1n0us · 2025-05-14T01:24:27Z


 wasi_nn_error
-load_by_name(const char *name, graph *g)
+load_by_name(char *name, uint32_t name_len, graph *g)


Since we have two sets of APIs for historical reasons, we might remove one in another PR. For now, let's ensure both are functional.

I suggest we use WASM_ENABLE_WASI_EPHEMERAL_NN on the wasm side.

With this flag, we declare two sets of APIs in wasi_nn.h. Please align with the content of native_symbols_wasi_nn in wasi_nn.c

lum1n0us · 2025-05-27T02:21:16Z

 wasm_load_by_name(const char *model_name, graph *g)
 {
-    wasi_nn_error res = load_by_name(model_name, g);
+    wasi_nn_error res = load_by_name(model_name, strlen(model_name), g);


better be

#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0 wasi_nn_error wasm_load_by_name(const char *model_name, graph *g) { wasi_nn_error res = load_by_name(model_name, strlen(model_name), g); return res; } #endif

HongxiaWangSSSS · 2025-05-27T07:43:02Z

 #include <stdint.h>
 #include "wasi_nn_types.h"

+#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0


Hi @ayakoakasaka and @lum1n0us ,
For wasi_nn and wasi_ephemeral_nn, different APIs need to be defined in the header file.
However, currently using wasi_ephemeral_nn, I find that I get an error when I calling set_input, ->Content is inconsistent when passed from wasm to native.
So can we divide it into two PRs, first support load_by_name in wasi-nn, and then implement support for wasi_ephemeral_nn

Sure. As a workaround.

add wasm load by name for WASI-NN

1df9b7c

HongxiaWangSSSS marked this pull request as ready for review May 12, 2025 05:24

HongxiaWangSSSS requested review from TianlongLiang, loganek, lum1n0us, no1wudi, wenyongh, xujuntwt95329 and yamt as code owners May 12, 2025 05:24

Merge branch 'bytecodealliance:main' into feature/support_wasm_load_b…

c5414fd

…y_name

yamt reviewed May 12, 2025

View reviewed changes

lum1n0us reviewed May 12, 2025

View reviewed changes

lum1n0us reviewed May 14, 2025

View reviewed changes

remove wasm_load_by_name from old wasi-nn

ff4ed2f

lum1n0us reviewed May 27, 2025

View reviewed changes

add wasi_ephemeral_nn in header file

2831ff2

HongxiaWangSSSS commented May 27, 2025

View reviewed changes

HongxiaWangSSSS closed this May 28, 2025

HongxiaWangSSSS mentioned this pull request May 28, 2025

add load_by_name in wasi-nn #4298

Merged

lum1n0us mentioned this pull request Jun 4, 2025

wasi-nn: make wasi_ephemeral_nn default #4326

Closed

	#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
	REG_NATIVE_FUNC(load, "(iii)i"),
	REG_NATIVE_FUNC(load_by_name, "(i)i"),
	REG_NATIVE_FUNC(load_by_name_with_config, "(ii*)i"),
	REG_NATIVE_FUNC(init_execution_context, "(i*)i"),
	REG_NATIVE_FUNC(set_input, "(ii*)i"),
	REG_NATIVE_FUNC(compute, "(i)i"),
	REG_NATIVE_FUNC(get_output, "(iii)i"),
	#else /* WASM_ENABLE_WASI_EPHEMERAL_NN == 0 */
	REG_NATIVE_FUNC(load, "(ii)i"),
	REG_NATIVE_FUNC(init_execution_context, "(i*)i"),
	REG_NATIVE_FUNC(set_input, "(ii*)i"),
	REG_NATIVE_FUNC(compute, "(i)i"),
	REG_NATIVE_FUNC(get_output, "(ii**)i"),
	#endif /* WASM_ENABLE_WASI_EPHEMERAL_NN != 0 */

	__attribute__((visibility("default"))) wasi_nn_error
	get_output(void *tflite_ctx, graph_execution_context ctx, uint32_t index,
	tensor_data output_tensor, uint32_t *output_tensor_size)

Conversation

HongxiaWangSSSS commented May 12, 2025

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

lum1n0us May 27, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

lum1n0us May 27, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

lum1n0us May 27, 2025 •

edited

Loading

lum1n0us May 27, 2025 •

edited

Loading