Upload README.md with huggingface_hub

README.md

@@ -60,7 +60,20 @@ delegate's blob for the output matmul. Tying them in PyTorch does not tie them h
 Referencing the weight through `F.linear` instead of the `proj_out` module does not either —
 exported both ways, whisper-tiny's decoder comes out at 198.0 MB exactly.
 
-
+**The decoder's int8 build is not shipped.** Dynamic int8 quantizes the linear weights and
+leaves the token embedding table in fp32, and that table is 79.7 MB — 51,865 tokens at
+384 dimensions. On this size that table is most of the file, so int8 lands at 110.2 MB against fp16's 99.1 MB — larger, because fp16 halves the table too. It converts and holds, but nothing would pick it, so it is not shipped.
+
+Until recently there was no decoder int8 build at all, and this card said PT2E was observing
+the int64 `decoder_input_ids`. That was wrong on both halves.
+`XNNPACKQuantizer.transform_for_annotation` rewrites every scalar argument of
+`add.Tensor`/`mul.Tensor` as `torch.tensor(float(arg))` whatever the node's dtype — one line
+in ExecuTorch's `backends/xnnpack/quantizer/xnnpack_quantizer_utils.py`, still present on
+main. In this decoder the casualty is `position_ids = torch.arange(...) + past_key_values_length`
+(`modeling_whisper.py:749`, `past_key_values_length` being a python `int`): it comes back
+float32, and the failure lands on `self.weight[position_ids]` — the **position** embedding
+lookup, not the token ids, and no observer involved. Measured by running `prepare_pt2e`
+with an empty quantizer and printing the failing node.
 
 ### Checked in the task's own units