Run WASM sessions at the default graph optimization level now that ort-web 1.31 loads the 8-bit decoders

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/worker/inference.worker.ts

@@ -260,14 +260,12 @@ async function createPipeline(
       const pipelineOptions: PretrainedModelOptions & { sequentialSessionLoad?: boolean } = {
         device,
         dtype,
-        // WASM sessions cap graph optimization at "basic" (D-014): the level-2
-        // QDQ transform in the bundled onnxruntime-web build rejects the 8-bit
-        // decoders' tied embed_tokens weight ("Missing required scale …
-        // DequantizeLinear"). q4 models use native MatMulNBits ops, so the
-        // lower level costs them nothing. WebGPU keeps the default level.
-        ...(device === "wasm" && {
-          session_options: { graphOptimizationLevel: "basic" as const },
-        }),
+        // No session_options: every backend runs at onnxruntime's default
+        // graph optimization level. D-014's WASM "basic" cap worked around a
+        // level-2 QDQ bug in ort-web 1.26.0-dev that rejected the 8-bit
+        // decoders; the 1.31.0-dev build bundled with Transformers.js 4.3.2
+        // loads them at every level (D-WS1c, pinned in
+        // tests/transformers-runtime.test.ts).
         progress_callback: forwardProgress,
         // D-027/D-029: sequential sub-model session loading trades load speed
         // for a lower peak-memory footprint — only worth it where the UI