BREAKTHROUGH: Delta+2-bit KV = 4-bit quality at 3 bpe (cosine 0.996)

Delta compression on key vectors: key[t]-key[t-1] has ~30% of absolute range.
2-bit quantization of delta matches 4-bit quality on absolute values.

Prototype results (head_dim=128, seq_len=1024):
  Direct 2-bit:  cosine 0.949 (3.0 bpe)
  Direct 4-bit:  cosine 0.995 (4.25 bpe)
  Delta+2-bit:   cosine 0.996 (3.04 bpe) ← EXCEEDS 4-bit!

No drift accumulation even without I-frames (pure delta, 0.996 cosine).
Implementation: compute delta before quantize, accumulate on dequant.

Next: integrate into engine and verify PPL.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: unamedkr

bench/data/ppl_results.csv

@@ -3,3 +3,6 @@ uniform_4b,998,2.490645,12.0691
 turbo_kv_1b,998,2.490645,12.0691
 turbo_kv_3b,998,2.490645,12.0691
 turbo_kv_1b+q4v,998,2.516130,12.3806
+uniform_4b,814,2.252016,9.5069
+uniform_3b,814,2.586115,13.2781
+uniform_2b_subblock,814,5.706569,300.8372