v2.2.0: end-to-end pipeline validation + GRPO no-tokenizer fallback

v2.1.0: fix N25 off-by-one, S2 reward_fn string safety

v20: fix N23/N24/M7/S2 - critical regression fixes from v1.9.0 audit

v19: fix N23-N25 + S1 reward functions + F1/F2/F3 documentation

v18: fix N18/N19/N20/N21/N22 Thinking Dial pipeline bugs

v17: fix Thinking Dial training pipeline (N10/N11/N12/N13/N14/N15/N16/N17)

v16-hotfix: fix kv_head_dim bug, add incremental gen test

v16: fix critical audit defects (N6/N7/N8/N9 + S3/S4/M2/M5)

v15: fix remaining audit issues (F1/F2/S1/M3/M8/doc)

v14 fix: F1 ThinkingDialModel thinking_embedding/gate 实际使用，F5 top_p NaN guard，M1 RoPE position_ids，M6 position_ids 传递链，DPO tokenizer 属性，forward() position_ids 参数

fix: 修复 F-NEW-13 GQA双重扩展 + S-NEW-13 GQA KV维度 + LOW清理

fix: 修复 SBLAttention forward_with_qkv() 形状错误和测试文件结构

Fix tests: FusionMiniLayer Q/K/V reshape + logging import + pytest compat

fix: external audit issues from commit 08f2cd2

fix: SBLAttention forward() guard for removed projections

fix: v13 external audit - CRITICAL/HIGH/MEDIUM fixes

fix: comprehensive audit fixes - CRITICAL/HIGH/MEDIUM/LOW

Feat: Add GGML/ONNX deployment and optimized SBLA attention (0.49ms)

fix(v12): resolve 6 defects from v11 audit (F-NEW-6, S-NEW-5, M-NEW-5/6, MI-NEW-4/5/6)

fix(v11): resolve remaining 5 defects (S-NEW-1/2, M-NEW-2/3, MI-NEW-1)

fix(v9): resolve 3 fatal + 1 serious + 1 moderate defects from external audit

fix: v6 audit - all critical/severe/moderate/minor defects

feat: implement S1 KV Cache + S2 GQA in SBLAttention

fix: F1 mask double-conversion NaN, F2 think token old format, S3 vocab sync, S1/S2 TODO, N1-N5

fix: v5 remove empty tokenizer.json, unify think tokens, integrate tokenizer into training pipeline

feat: train SentencePiece tokenizer + update README

chore: replace author real name with GitHub username

fix: v4 comprehensive defect repair (S3/M1/M3/M4/M5/F2/F3)

feat: M4 attention unification + DPO trainer + inference dashboard

fix: v3 comprehensive defect repair

feat: 重写 DyQuant 量化代码，修复 thinking_dial.py 编码问题

fix: 修复 S1-S4/M2-M4 缺陷，规范化工程结构

fix: FusionModel forward propagation loss=NaN

feat: 完成 SBLA 注意力集成 + MVP 训练流程

feat: 初始化 Fusion 项目 - 六边形开源大模型