refactor(phase-01): v3 retune fast & balanced roles

fast (Gemma 4 26B-A4B):
- Enable mmproj GPU loading (vision ~1s, 12x faster than CPU)
- KV f16 → q8_0 (save ~2.5 GB VRAM for mmproj)
- Tensor split 0.5,0.5 → 0.43,0.57 (13/17 layers)
- Remove --mlock/--poll/--prio/-t/-tb (no measurable impact)
- measured_tps 74.65 → 71.89 (trade 3.7% speed for vision)

balanced (Qwen 3.5 35B-A3B):
- Tensor split 0.5,0.5 → 0.48,0.52 (enables pipeline parallelism)
- Ubatch 128 → 256 (prefill +78%: 649 → 1,157 t/s)
- mmproj + --no-mmproj-offload (CPU vision, VRAM headroom)
- Remove useless flags same as fast
- measured_tps 61.62 → 64.16 (+4.1%)

Other:
- Document full retuning in docs/v3_{fast,balanced}_retuning_log.md
- Session report at .planning/reports/20260411-session-report.md
- Add bench utilities: bench_short/bench_long/test_ts_ratios
- Speculative decoding (E2B draft) experimented but rejected
  (+14% gen vs -31% cold start + tokenizer mismatch + mmproj conflict)

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

.planning/STATE.md

@@ -3,8 +3,8 @@ gsd_state_version: 1.0
 milestone: v1.1
 milestone_name: milestone
 status: planning
-last_updated: "2026-04-08T01:58:00.000Z"
-last_activity: 2026-04-08
+last_updated: "2026-04-11T10:30:00.000Z"
+last_activity: 2026-04-11
 progress:
   total_phases: 3
   completed_phases: 2
@@ -32,7 +32,7 @@ Last activity: 2026-04-08
 
 ## Completed Phases
 
-- Phase 01 (LLM Tuning): 5개 모델 최적 설정 확정 (74.65 / 61.62 / 16.0 / 16.7 / 8.95 t/s)
+- Phase 01 (LLM Tuning): 5개 모델 최적 설정 확정 (71.89‡ / 64.16† / 16.0 / 16.7 / 8.95 t/s) — † balanced / ‡ fast 2026-04-11 재튜닝
 - Phase 02 (API Engine): Variet Engine v1.0 — FastAPI 프록시 + 핫스왑 + 503 보호
 
 ## Recent Decisions
@@ -43,6 +43,8 @@ Last activity: 2026-04-08
 - Variet Engine: 단일 포트(8000) FastAPI 리버스 프록시.
 - config/engine_models.json → 모든 설정의 Single Source of Truth.
 - CLI-First 검증 전략: VS Code Extension 전 OpenClaude CLI로 에이전트 루프 먼저 검증.
+- balanced 역할 v3 재튜닝 (2026-04-11): `-ub 256`, `-ts 0.48,0.52`, `--no-mmproj-offload`, 보조 옵션(mlock/poll/prio) 제거. 실측 61.62 → 64.16 t/s. prefill 649 → 1,157 t/s (+78%). 상세: `docs/v3_balanced_retuning_log.md`.
+- fast 역할 v3 재튜닝 (2026-04-11): `cache-type q8_0`, `-ts 0.43,0.57`, `--mmproj` GPU 적재, 보조 옵션 제거. 실측 74.65 → 71.89 t/s (-3.7%). Vision GPU 지원 추가 (이미지 인코딩 ~1초). Speculative Decoding (E2B draft) 실험 후 채택 안 함. 상세: `docs/v3_fast_retuning_log.md`.
 
 ## Roadmap Evolution
 
@@ -58,6 +60,5 @@ None.
 
 ## Session Continuity
 
-Last session: 2026-04-08T10:58:00+09:00
-Stopped at: Phase 05 PLAN created, user will execute manually
-Resume file: .planning/phases/05-vscode-extension-packaging/.continue-here.md
+Last session: 2026-04-11T10:30:00+09:00
+Stopped at: balanced 역할 v3 재튜닝 완료 — config/engine_models.json, docs/v3_balanced_retuning_log.md, Phase 01 VERIFICATION.md 증적 저장 완료. 다음 작업 선택 대기.