Upload README.md with huggingface_hub

README.md

@@ -66,12 +66,15 @@ leaves the token embedding table in fp32, and that table is 159.3 MB — 51,865
 768 dimensions. On this size the rest of the decoder finally outweighs it: int8 comes in at 315.5 MB against fp16's 387.3 MB, so it is the smallest portable build and it ships.
 
 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. `XNNPACKQuantizer.transform_for_annotation`
-rewrites every scalar argument of `add.Tensor`/`mul.Tensor` as `torch.tensor(float(arg))`
-whatever the node's dtype, so the `arange(n) + 0` that builds the attention mask came back
-float32 and could no longer index — one line in ExecuTorch's
-`backends/xnnpack/quantizer/xnnpack_quantizer_utils.py`, still present on main, and nothing
-to do with the token ids.
+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