everything-lane: rung docs + FP8-vision note

serving/everything-lane/Dockerfile

@@ -5,13 +5,15 @@
 #   - kvq.py / kvq_kernels.py + the mla/sparse_mla/kv_cache/flashinfer files:
 #     compact KV rows for the sparse-MLA layers, gated by VLLM_KVQ_TILES.
 #     "8888" repacks the fp8_ds_mla row 656->528 B (bit-identical: the 128 B
-#     RoPE slot is provably inert -- qk_rope_head_dim=0); "6666" stores the
-#     512 B latent as 4 fp6 tiles (416 B/row) -- what makes 512k+MTP KV fit.
+#     RoPE slot is provably inert -- qk_rope_head_dim=0); "8666" (1 fp8 +
+#     3 fp6 tiles, 444 B/row) is the shipped 512k+MTP rung (TF 95.57%);
+#     "6666" (all-fp6, 416 B/row) trades ~1.5 TF points for a thinner pin.
 #     Decode/prefill re-stage top-k rows into canonical 656 B staging consumed
 #     by the unmodified FlashInfer SM120 cubin. Unset = stock path, no change.
 #   - model.py / modelopt.py: the 512k lane's files plus quant_config
-#     passthrough for the embedding/vision construction sites (superset;
-#     vision stays BF16)
+#     passthrough for the embedding/vision construction sites (manifest-gated:
+#     the shipped checkpoint's block-FP8 vision tower loads through it;
+#     BF16-tower checkpoints construct bit-identically to the base image)
 ARG BASE=local/vllm-glm53:fp8attn-512k
 FROM ${BASE}
 ARG V=/usr/local/lib/python3.12/dist-packages/vllm