Upload README.md with huggingface_hub

README.md

@@ -40,13 +40,16 @@ retrieves worse.
 
 | build | file | size (MB) | Mac ms* | backend takes | worst cosine vs eager | retrieval budget |
 |---|---|---|---|---|---|---|
-| fp32 | `embed_multilingual_e5_small_xnnpack_fp32.pte` | 470.2 | 89.8 | 78.5% | 1.000000 | 0% |
-| fp16 | `embed_multilingual_e5_small_xnnpack_fp16.pte` | 235.2 | 41.8 | 67.6% | 1.000000 | 1% |
-| Core ML (fp16, iOS) | `embed_multilingual_e5_small_coreml_all.pte` | 235.8 | 4.9 | 100.0% | 0.999979 | 15% |
+| fp32 | `embed_multilingual_e5_small_xnnpack_fp32.pte` | 470.2 | 21.3 | 78.5% | 1.000000 | 0% |
+| fp16 | `embed_multilingual_e5_small_xnnpack_fp16.pte` | 235.2 | 31.4 | 67.6% | 1.000000 | 1% |
+| Core ML (fp16, iOS) | `embed_multilingual_e5_small_coreml_all.pte` | 235.8 | 3.9 | 100.0% | 0.999979 | 15% |
 
-\*Mac arm64, median of 10, one 256-token sequence — a reference point for relative
-cost, not a device number. Torch eager fp32 on the same machine is
-124.0 ms.
+\*Mac arm64, one 256-token sequence, **fastest of five medians of ten** — a reference
+point for relative cost, not a device number. The host shares its cores with other work,
+and a single median does not survive that: the same eager model here measured 19.6 ms and
+182.8 ms twenty minutes apart. Contention only ever adds time, so the fastest repetition is
+the one that means something. Torch eager fp32, measured the same way, is
+18.9 ms.
 
 Cosine is measured against the model run in eager through its own pooling, over eight
 sentences. The last column is the one that decides: rank those eight against each
@@ -56,18 +59,21 @@ top-1 results.
 
 ## The attention is eager, and that is the faster export
 
-On the sdpa path transformers hands `F.scaled_dot_product_attention` a **boolean**
-mask, PyTorch fills the masked entries with `-inf`, and the edge dialect lowers the
-whole thing to `_safe_softmax` — whose guard against a row of all `-inf` costs six
-operations XNNPACK cannot take (`scalar_tensor`, `where`, `logical_not`, `eq`,
-`full_like`, `any.dim`), once per attention block, each one cutting the subgraph in two.
-
-`attn_implementation="eager"` masks with `torch.finfo(dtype).min` instead — a large
-finite number — so there is no guard to lower. The two disagree only about rows that
-have no unmasked key at all: sdpa zeroes them, eager gives them a uniform row. Those
-are padding rows, which the pooling discards and which every real query row masks out,
-so the output does not move. Measured with all but eight positions masked — as
-adversarial as this shape gets — the two graphs agree to 1.4e-07.
+`F.scaled_dot_product_attention` does not survive export as one operation. The edge
+dialect lowers it through `_safe_softmax`, whose guard against a row with no unmasked key
+at all leaves **11 operations XNNPACK cannot take, in every attention
+block** — `scalar_tensor`, `where`, `mul.Scalar`, `logical_not`, `eq`, `full_like`, `any.dim`. Each one cuts the subgraph in two.
+
+The switch is `attn_implementation="eager"`: transformers then builds the mask
+itself, as `torch.finfo(dtype).min`, instead of handing `F.sdpa` a **boolean** mask
+for PyTorch to fill with `-inf`.
+
+The guard is emitted whether or not it can ever fire, and here it cannot: it triggers only
+on `-inf`, and this arm never produces one. So the two differ only about rows that have no
+unmasked key at all — sdpa zeroes them, this one gives them a uniform row — and those are
+padding rows, which the pooling discards and which every real query row masks out anyway.
+Measured with all but eight positions masked, as adversarial as this shape gets, the two
+graphs agree to 1.4e-07.
 
 XNNPACK fp32 goes from **62.6% to 78.5%** delegated.