Fixed for decoder dl speed and mobile warnings on low memory devices.

2026-07-29 07:47:42 +02:00
parent 2643a446d0
commit 78e99fc415
7 changed files with 208 additions and 32 deletions
@@ -1,8 +1,11 @@
+diff --git a/node_modules/@huggingface/transformers/.bun-tag-8719566ebeed846f b/.bun-tag-8719566ebeed846f
+new file mode 100644
+index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
 diff --git a/dist/transformers.web.js b/dist/transformers.web.js
-index bb7b32717a42475a5f66411a33d5e5964dfda3e2..799cb402e98d8d0d58bf59629c4c2992407477e0 100644
+index bb7b32717a42475a5f66411a33d5e5964dfda3e2..03de63967e99f8f3c847858621d72577ef037391 100644
 --- a/dist/transformers.web.js
 +++ b/dist/transformers.web.js
-@@ -18558,22 +18558,28 @@ async function getSession(pretrained_model_name_or_path, fileName, options, cach
+@@ -18558,22 +18558,49 @@ async function getSession(pretrained_model_name_or_path, fileName, options, cach
   return { buffer_or_path, session_options, session_config };
 }
 async function constructSessions(pretrained_model_name_or_path, names, options, cache_sessions = void 0) {
@@ -22,14 +25,35 @@ index bb7b32717a42475a5f66411a33d5e5964dfda3e2..799cb402e98d8d0d58bf59629c4c2992
 -      })
 -    )
 -  );
-+  // Patched (au_whisper_web): load sub-model sessions one at a time instead of
-+  // Promise.all-ing them. Each entry briefly holds a full-size decoded model
-+  // buffer in JS-heap memory (on top of onnxruntime-web's own WASM-heap copy
-+  // during session creation); loading Whisper's encoder and decoder
+  // Patched (au_whisper_web): each entry briefly holds a full-size decoded
+  // model buffer in JS-heap memory (on top of onnxruntime-web's own WASM-heap
+  // copy during session creation); loading Whisper's encoder and decoder
 +  // concurrently keeps both buffers alive at once and roughly doubles the
 +  // load-time memory peak, which is enough to OOM-crash mobile browsers on
-+  // larger models (e.g. medium, ~460 MB combined). Sequential loading lets the
-+  // previous entry's buffer become garbage before the next one is fetched.
+  // larger models (e.g. medium, ~460 MB combined). `options.sequentialSessionLoad`
+  // (set by the caller only when that risk is real, D-027/D-029) loads
+  // sub-model sessions one at a time instead of Promise.all-ing them, so the
+  // previous entry's buffer becomes garbage before the next one is fetched —
+  // at the cost of losing the download concurrency a fast connection could
+  // otherwise use, which is the default (and always was, pre-D-027).
+  if (!options?.sequentialSessionLoad) {
+    return Object.fromEntries(
+      await Promise.all(
+        Object.keys(names).map(async (name) => {
+          const cache_config = cache_sessions?.[name] ?? false;
+          const { buffer_or_path, session_options, session_config } = await getSession(
+            pretrained_model_name_or_path,
+            names[name],
+            options,
+            cache_config,
+            name
+          );
+          const session = await createInferenceSession(buffer_or_path, session_options, session_config);
+          return [name, session];
+        })
+      )
+    );
+  }
 +  const entries = [];
 +  for (const name of Object.keys(names)) {
 +    const cache_config = cache_sessions?.[name] ?? false;