Pablo Claude Opus 4.7 (1M context) commited on
Commit
cf99605
·
1 Parent(s): da68829

docs: wire 5 dashboard/benchmark screenshots into README

Browse files

Live Demo section: dashboard_live_demo.png (With vs Without comparison).
V6 Live Snapshot block: dashboard_v6_snapshot.png + dashboard_aiter_config.png.
Benchmark section: benchmark_v6_terminal.png under the 8/8 targets table.
Key Stats section: dashboard_key_stats.png next to the stats table.

assets/screenshots/.gitkeep documents the 5 expected filenames.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Files changed (2) hide show
  1. README.md +25 -13
  2. assets/screenshots/.gitkeep +9 -0
README.md CHANGED
@@ -82,21 +82,11 @@ Every optimization traces back to a peer-reviewed paper published at **NeurIPS,
82
 
83
  ## 🎬 Live Demo
84
 
85
- Real metrics from `demo/app.py` running against the full ContextForge stack — five agents, real Qwen3 tokenizer, real LSH+FAISS dedup, INV-15 enforced live.
86
 
87
  <p align="center">
88
- <img src="assets/screenshots/dashboard_live.png" alt="Live Demo tab query input" width="900"><br>
89
- <em>Live Demo tab — type a multi-agent query and run it through both paths.</em>
90
- </p>
91
-
92
- <p align="center">
93
- <img src="assets/screenshots/dashboard_results.png" alt="Live Demo with ContextForge — 79.85% savings, INV-15 firing" width="900"><br>
94
- <em>With ContextForge: <b>263 → 53 tokens (79.85 % savings)</b>, JCR Safety Gate fires INV-15 on the Critic.</em>
95
- </p>
96
-
97
- <p align="center">
98
- <img src="assets/screenshots/dashboard_v6_snapshot.png" alt="Architecture tab — V6 Live Snapshot" width="900"><br>
99
- <em>Architecture tab — TokenDance + JCR Safety Gate + AITER ROCm config snapshots.</em>
100
  </p>
101
 
102
  ```
@@ -118,6 +108,18 @@ strategy: register+lsh+faiss
118
  reason: INV-15: judge role='critic' risk=1.00 > threshold=0.70 → dense prefill mandated
119
  ```
120
 
 
 
 
 
 
 
 
 
 
 
 
 
121
  ---
122
 
123
  ## 🏗️ Architecture
@@ -204,6 +206,11 @@ flowchart TB
204
  | JCR INV-15 violations | **0** | 0 | ✅ |
205
  | JCR Critic dense rate (high-risk sweep) | **1.000** | ≥ 0.5 | ✅ |
206
 
 
 
 
 
 
207
  ---
208
 
209
  ## 📈 Key Stats
@@ -220,6 +227,11 @@ flowchart TB
220
  | Peer-reviewed papers implemented | **10** |
221
  | System invariants enforced | **15** |
222
 
 
 
 
 
 
223
  ---
224
 
225
  ## 🚀 Quick Start
 
82
 
83
  ## 🎬 Live Demo
84
 
85
+ Real metrics from `demo/app.py` running against the full ContextForge stack — five agents, real Qwen3 tokenizer, real LSH+FAISS dedup, INV-15 enforced live. Side-by-side comparison: **263 → 53 tokens, 79.85 % savings** with ContextForge; passthrough on the right.
86
 
87
  <p align="center">
88
+ <img src="assets/screenshots/dashboard_live_demo.png" alt="Live Demo — With vs Without ContextForge, 79.85% savings, INV-15 firing on the Critic" width="960"><br>
89
+ <em>Live Demo tab — left: query input. Right: <b>With ContextForge</b> (79.85 % savings, INV-15 fires on the Critic) vs. <b>Without ContextForge</b> (passthrough, 0 % savings).</em>
 
 
 
 
 
 
 
 
 
 
90
  </p>
91
 
92
  ```
 
108
  reason: INV-15: judge role='critic' risk=1.00 > threshold=0.70 → dense prefill mandated
109
  ```
110
 
111
+ ### V6 Live Snapshot — TokenDance + JCR Safety Gate
112
+
113
+ <p align="center">
114
+ <img src="assets/screenshots/dashboard_v6_snapshot.png" alt="Architecture tab — TokenDance Master-Mirror + JCR Safety Gate live snapshots" width="640"><br>
115
+ <em>Architecture tab — <b>TokenDance Master-Mirror Storage</b> (5-agent demo, 4.71× compression) and <b>JCR Safety Gate</b> firing INV-15 (risk = 1.000, dense_prefill = True).</em>
116
+ </p>
117
+
118
+ <p align="center">
119
+ <img src="assets/screenshots/dashboard_aiter_config.png" alt="AITER ROCm Config — MI300X" width="520"><br>
120
+ <em>AITER ROCm Config (MI300X) — <code>rocm_available: True</code>, 7 documented env vars, AMD-published speedups: 3× fused MoE, 2× block-scale GEMM, 2-4× FP8 memory.</em>
121
+ </p>
122
+
123
  ---
124
 
125
  ## 🏗️ Architecture
 
206
  | JCR INV-15 violations | **0** | 0 | ✅ |
207
  | JCR Critic dense rate (high-risk sweep) | **1.000** | ≥ 0.5 | ✅ |
208
 
209
+ <p align="center">
210
+ <img src="assets/screenshots/benchmark_v6_terminal.png" alt="V6.0 benchmark terminal output — S-14 token_dance 10.81x, S-15 jcr_gate 0 violations" width="780"><br>
211
+ <em>Live terminal output of <code>python demo/benchmark_v5.py</code> — S-14 TokenDance <b>10.81×</b> compression with reconstruction error <b>1.19e-07</b>, S-15 JCR Safety Gate <b>0 INV-15 violations</b>.</em>
212
+ </p>
213
+
214
  ---
215
 
216
  ## 📈 Key Stats
 
227
  | Peer-reviewed papers implemented | **10** |
228
  | System invariants enforced | **15** |
229
 
230
+ <p align="center">
231
+ <img src="assets/screenshots/dashboard_key_stats.png" alt="Architecture tab — Key Statistics panel" width="520"><br>
232
+ <em>Key Statistics panel rendered live in the dashboard's Architecture tab.</em>
233
+ </p>
234
+
235
  ---
236
 
237
  ## 🚀 Quick Start
assets/screenshots/.gitkeep ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ # Drop the 5 dashboard / benchmark screenshots in this directory:
2
+ #
3
+ # dashboard_live_demo.png — Live Demo tab (With vs Without ContextForge, 79.85% savings)
4
+ # dashboard_v6_snapshot.png — Architecture tab V6 Live Snapshot (TokenDance + JCR Safety Gate)
5
+ # dashboard_aiter_config.png — AITER ROCm Config table + documented speedups
6
+ # dashboard_key_stats.png — Key Statistics panel
7
+ # benchmark_v6_terminal.png — V6.0 METRICS terminal output (S-14 + S-15)
8
+ #
9
+ # README.md references them at these exact paths.