Core ML: pin compute_unit=CPU_ONLY, drop the fp32 variant

These graphs fail the Apple Neural Engine path (coremltools#2825 masked mean-pool over a dynamic sequence dim; clip-text additionally ANECCompile FAILED). Core ML still returned correct output because it silently fell back to CPU, but the failed ANE compile was paid on every call. Pinning compute_unit=CPU_ONLY skips the attempt.

Measured on an iPhone 16, fp16, 3 warmup + 15 timed runs, median:
all-MiniLM 13.7 ms -> 2.5 ms 5.5x
multi-qa 14.1 ms -> 2.5 ms 5.6x
paraphrase-L12 26.9 ms -> 4.2 ms 6.4x
distiluse 33.0 ms -> 8.0 ms 4.1x
clip-text 18.1 ms -> 4.9 ms 3.7x

The fp32 variant is removed. Once fp16 is pinned it is dominated on both axes: slower (all-MiniLM 4.5 vs 2.5 ms, clip-text 9.5 vs 4.9 ms) and twice the size. Output fidelity against fp32 was gated first: relative L2 4e-6 (all-MiniLM, multi-qa), 0.0010 (paraphrase), 0.0046 (distiluse).

v0.9.0 and below are untouched.

coreml/all_minilm_l6_v2_coreml_fp16.pte

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8319154dc5c535b46710e125c4c29359d49562a316201cc023f60115f1314d7c
-size 45460224
+oid sha256:9a08b1c452315aa2f25b4bc5b19ca688166a349e3ebe9d1ec6fc61b811ac571e
+size 45460244

coreml/all_minilm_l6_v2_coreml_fp32.pte

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5156e7c3908a8853c4493e942b70508246f7de7d2500259fcb188fc23d5f7e06
-size 90545948

coreml/config.json

@@ -42,41 +42,6 @@
           ]
         }
       }
-    },
-    {
-      "file": "all_minilm_l6_v2_coreml_fp32.pte",
-      "precision": "fp32",
-      "quantized": false,
-      "default": false,
-      "methods": {
-        "forward": {
-          "inputs": [
-            {
-              "shape": [
-                1,
-                254
-              ],
-              "dtype": "int64"
-            },
-            {
-              "shape": [
-                1,
-                254
-              ],
-              "dtype": "int64"
-            }
-          ],
-          "outputs": [
-            {
-              "shape": [
-                1,
-                384
-              ],
-              "dtype": "float32"
-            }
-          ]
-        }
-      }
     }
   ]
 }