Delete the miscalibrated sm_120 SAME-S fp8 encoder

Its activation quantisers were calibrated with a percentile-of-percentile plus a
1e-4 floor, putting the clip points far below where the decoder's plain amax puts
them. The equivalent sm_90 engine was deleted when that was found; this copy was
missed and only surfaced when the deprecated engines were swept into legacy/.

Keeping it under legacy/ would have left a trap: it is the one file there that is
wrong rather than merely superseded, and anyone building sm_120 from it would
inherit the bug. The recalibrated weights live in onnx/same-s/enc_fp8.onnx, which
build_autoencoders.py uses to produce enc_fp8_chunkable.trt.

tensorRT/sm_120/same-s/legacy/enc_fp8.trt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a5b4ca020906abfd3235f81dbe0890807b22fd36ea496fc1f93b18175b873081
-size 78675460