Optimize yolox_l_1024x640_w8 for full-ANE execution

Replace the YOLOX-L Core ML package with a re-converted build that keeps
every operation on the Apple Neural Engine, eliminating the CPU-bound ops
in the previous conversion. Functionally equivalent (same YOLOX-L model,
1024x640 input, 8-bit weights); same archive layout and I/O contract.

Update README.md with the new SHA-256 checksum and conversion toolchain
(torch 2.12.1).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

README.md

@@ -76,7 +76,8 @@ YOLOX-L anchor-free object detector, converted to Core ML at a fixed
   (`(cx, cy, w, h)` in model-input pixels plus sigmoid class scores).
 - **Precision:** 8-bit weight quantization, FP16 compute.
 - **Upstream:** [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX) (Megvii Inc.) — Apache-2.0.
-- **Conversion:** coremltools 9.0 from TorchScript (`torch==2.7.0`).
+- **Conversion:** coremltools 9.0 from TorchScript (`torch==2.12.1`); all
+  operations placed on the Apple Neural Engine (no CPU fallback ops).
 
 ### `silero-vad-unified-v6`
 
@@ -100,7 +101,7 @@ SHA-256 checksums of the archives:
 
 ```
 3940398c2518ac5f01c09f5f5eab868c2b217ab53c7d9a145d2387e76251b5d5  qwen3_5_mlx_4b_vision_vid_512x320_w8.tar
-133cd460061c943a042a4d69090825f83941725db2097b4e8ebae9802b956cd3  yolox_l_1024x640_w8.tar
+7f7bf85947bb228f978470284e16a9d00c906a6cb07359f9a51c68806fa9c609  yolox_l_1024x640_w8.tar
 ee14d006d1cea87f15a4f0ac5f3e1e00b80a10c40eca855e8ff6741f389b4423  silero-vad-unified-v6.tar
 ```
 

yolox_l_1024x640_w8.tar

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133cd460061c943a042a4d69090825f83941725db2097b4e8ebae9802b956cd3
+oid sha256:7f7bf85947bb228f978470284e16a9d00c906a6cb07359f9a51c68806fa9c609
 size 54605824