Spaces:
Running
Running
File size: 31,400 Bytes
930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 533b008 124f5a3 533b008 d24dca8 533b008 d24dca8 533b008 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 613243b 930e291 d24dca8 930e291 72148e6 930e291 d24dca8 930e291 72148e6 db777f7 72148e6 930e291 72148e6 d24dca8 930e291 72148e6 930e291 72148e6 930e291 67081eb 72148e6 930e291 02e9bc2 d24dca8 67081eb 930e291 96c2919 930e291 d24dca8 930e291 ae650e1 d24dca8 ae650e1 d24dca8 ae650e1 930e291 ae650e1 d24dca8 b7d4c7a ae650e1 d24dca8 ae650e1 d24dca8 ae650e1 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 ae650e1 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 ae650e1 d24dca8 ae650e1 930e291 d24dca8 ae650e1 d24dca8 ae650e1 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 d24dca8 930e291 613243b 930e291 6e85609 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 | <!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Kalpana AI โ O(1) RIF Neural Studio & Benchmarks</title>
<!-- Fonts -->
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link href="https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@400;500;600;700&family=Outfit:wght@300;400;500;600;700;800&display=swap" rel="stylesheet">
<!-- KaTeX for formulas -->
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.16.8/dist/katex.min.css">
<script defer src="https://cdn.jsdelivr.net/npm/katex@0.16.8/dist/katex.min.js"></script>
<link rel="stylesheet" href="./style.css">
</head>
<body>
<div class="app-layout">
<!-- Navigation Top Bar -->
<header class="top-nav">
<div class="brand">
<div class="logo-badge">K</div>
<div>
<div class="logo-title">Kalpanฤ AI Studio</div>
<div class="logo-sub">O(1) Resonant Interference Field Substrate ยท Patent LK/P/1/24089</div>
</div>
</div>
<nav class="nav-tabs">
<button class="nav-tab active" data-tab="tab-chat">๐ฌ Live Neural Chat</button>
<button class="nav-tab" data-tab="tab-benchmark">๐ฌ Benchmarks & Haystack</button>
<button class="nav-tab" data-tab="tab-architecture">๐๏ธ Layer Architecture</button>
<button class="nav-tab" data-tab="tab-swagger">๐ Swagger API</button>
<button class="nav-tab" data-tab="tab-economics">๐ฐ Unit Economics</button>
</nav>
<div class="header-status">
<span class="status-indicator" id="headerStatusDot"></span>
<span id="headerStatusText">O(1) RIF GPU Active (96.00 MB ยท 24 Layers)</span>
</div>
</header>
<!-- Main Content Container -->
<div class="tab-content-container">
<!-- ============================================================ -->
<!-- TAB 1: LIVE NEURAL CHAT (FULL WIDTH CLEAN INTERFACE) -->
<!-- ============================================================ -->
<section class="tab-pane active" id="tab-chat">
<div class="chat-container">
<!-- Neural GPU Telemetry & Health Bar -->
<div class="chat-telemetry-bar">
<div class="telemetry-item">
<span class="pulse-dot" id="serverPulse"></span>
<span class="telemetry-label">GPU Backend:</span>
<span class="telemetry-val val-green" id="serverStatusVal">NVIDIA GPU ยท Online</span>
</div>
<div class="telemetry-item">
<span class="telemetry-label">Attention Routing:</span>
<span class="telemetry-val val-cyan">24 / 24 Layers Intercepted</span>
</div>
<div class="telemetry-item">
<span class="telemetry-label">O(1) KV Memory:</span>
<span class="telemetry-val val-green">96.00 MB (Strict O(1))</span>
</div>
<div class="telemetry-item">
<span class="telemetry-label">Harmonic Bands:</span>
<span class="telemetry-val val-purple">2,048 Bands</span>
</div>
<button class="btn-ping" id="btnPingServer" title="Test real-time connection to GPU backend">
๐ Ping Server
</button>
</div>
<!-- Chat History Stream -->
<main class="chat-main-full">
<div class="chat-history" id="chatHistory">
<div class="chat-bubble bot-bubble">
<div class="bubble-header">
<span class="bubble-avatar">K</span>
<span class="bubble-author">Kalpana AI</span>
<span class="bubble-badge">Qwen2.5-0.5B + RIF</span>
</div>
<div class="bubble-body">
Hello! ๐ I am **Kalpana AI**, powered by the **Qwen2.5-0.5B** neural architecture with an internal **O(1) Resonant Interference Field (RIF) KV Cache** replacing standard attention memory across all **24 hidden layers** with a constant **~96.00 MB VRAM** footprint ($O(1)$ invariant).
How can I help you today?
- Ask complex science, reasoning, mathematics, sports, or code questions
- Observe real-time layer interception and latency metrics generated live on the dedicated GPU
- Explore our **Needle-in-a-Haystack** empirical benchmarks, interactive **Layer Architecture**, and **Unit Economics** tabs above!
</div>
</div>
</div>
<!-- Generating Progress Indicator Bar -->
<div class="gen-progress-bar" id="genProgressBar" style="display: none;">
<div class="progress-track">
<div class="progress-fill"></div>
</div>
<div class="progress-text">โก Routing prompt through 24 RIF Attention Layers on GPU...</div>
</div>
<!-- Input Bar -->
<div class="chat-input-wrapper">
<div class="chat-input-bar">
<textarea id="chatInput" placeholder="Ask anything, test math, physics, reasoning, or code... (Press Enter to Send)" rows="1"></textarea>
<button id="btnSendChat" class="btn-send" title="Send query to Kalpana RIF Engine">
<svg width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5"><line x1="22" y1="2" x2="11" y2="13"/><polygon points="22 2 15 22 11 13 2 9 22 2"/></svg>
</button>
</div>
<div class="input-caption">
Direct neural forward-pass through <code>KalpanaDynamicCache</code> on dedicated NVIDIA GPU ยท Strict O(1) Memory Invariance.
</div>
</div>
</main>
</div>
</section>
<!-- ============================================================ -->
<!-- TAB 2: BENCHMARKS & NEEDLE-IN-A-HAYSTACK -->
<!-- ============================================================ -->
<section class="tab-pane" id="tab-benchmark">
<div class="pane-inner">
<div class="section-header">
<h2>๐ฌ Empirical Retrieval & Memory Benchmarks</h2>
<p>Evaluating long-context recall across 500 semantic chunks (~12,500 tokens) and memory scaling bounds.</p>
</div>
<!-- Needle in Haystack Live Runner -->
<div class="content-card">
<div class="card-head">
<h3>๐ฏ Needle-in-a-Haystack Test Suite (500 Chunks / 2,048 Bands)</h3>
<button class="btn-primary" id="btnRunHaystack" style="width: auto; padding: 0.5rem 1.2rem;">
โถ Run Live Test Suite
</button>
</div>
<div class="benchmark-grid">
<div class="haystack-card" id="needle1Card">
<div class="needle-badge">NEEDLE 1 ยท 10% DEPTH (t=50)</div>
<div class="needle-query">"What is the secret passkey for Project Chronos?"</div>
<div class="needle-result">
<span class="status-tag tag-pass">EXACT HIT (Resonance: 0.8935)</span>
<div class="retrieved-text">"The secret passkey for Project Chronos is OMEGA-7749."</div>
</div>
</div>
<div class="haystack-card" id="needle2Card">
<div class="needle-badge">NEEDLE 2 ยท 50% DEPTH (t=250)</div>
<div class="needle-query">"Who invented the resonant hyper-drive?"</div>
<div class="needle-result">
<span class="status-tag tag-pass">EXACT HIT (Resonance: 0.7880)</span>
<div class="retrieved-text">"Dr. Elena Vance invented the resonant hyper-drive in Neo-Geneva."</div>
</div>
</div>
<div class="haystack-card" id="needle3Card">
<div class="needle-badge">NEEDLE 3 ยท 90% DEPTH (t=450)</div>
<div class="needle-query">"What is the emergency shutdown code for reactor 4?"</div>
<div class="needle-result">
<span class="status-tag tag-pass">EXACT HIT (Resonance: 0.8293)</span>
<div class="retrieved-text">"The emergency shutdown code for reactor 4 is EPSILON-9021."</div>
</div>
</div>
</div>
<div class="stats-banner">
<div class="stat-box">
<div class="stat-number">100.0%</div>
<div class="stat-label">Retrieval Accuracy (3/3 Exact Hits)</div>
</div>
<div class="stat-box">
<div class="stat-number">96.00 MB</div>
<div class="stat-label">Active Memory Footprint (Strict O(1))</div>
</div>
<div class="stat-box">
<div class="stat-number">20.2</div>
<div class="stat-label">Ingestion Speed (chunks / sec)</div>
</div>
<div class="stat-box">
<div class="stat-number">0.00 ms</div>
<div class="stat-label">Prompt Re-Transmission Overhead</div>
</div>
</div>
</div>
<!-- โ๏ธ Live Head-to-Head Benchmark Suite -->
<div class="content-card" style="margin-top: 1.5rem; border-color: rgba(124, 58, 237, 0.4);">
<div class="card-head">
<div>
<h3 style="color: #c084fc;">โ๏ธ Live Head-to-Head Benchmark: Baseline Qwen vs. Kalpana RIF Qwen</h3>
<p style="font-size: 0.82rem; color: var(--text-muted); margin-top: 0.2rem;">
Real-time tensor footprint comparison across expanding token horizons (2K to 1M tokens) based on verified PyTorch attention equations.
</p>
</div>
<button class="btn-primary" id="btnRunH2H" style="width: auto; padding: 0.5rem 1.2rem; background: linear-gradient(135deg, #7c3aed, #00f0ff);">
โถ Run Live Head-to-Head Test
</button>
</div>
<!-- Dynamic Comparison Columns -->
<div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(320px, 1fr)); gap: 1.2rem; margin-top: 1rem;">
<!-- Model A: Baseline Qwen (Standard KV Cache) -->
<div style="background: rgba(255, 51, 102, 0.04); border: 1px solid rgba(255, 51, 102, 0.3); border-radius: 10px; padding: 1.2rem;">
<div style="display: flex; justify-content: space-between; align-items: center; margin-bottom: 0.8rem;">
<span style="font-weight: 700; color: var(--red); font-size: 0.95rem;">๐ซ Baseline Qwen (Standard KV Cache)</span>
<span class="status-tag tag-fail" id="baselineStatusTag">O(N) Linear Growth</span>
</div>
<div style="font-size: 0.8rem; color: var(--text-muted); margin-bottom: 1rem;">
Tensor scaling: <code>torch.cat([cache, new_kv], dim=-2)</code> across all 24 layers.
</div>
<div style="display: flex; flex-direction: column; gap: 0.7rem;">
<div>
<div style="display: flex; justify-content: space-between; font-size: 0.8rem; margin-bottom: 0.2rem;">
<span style="color: var(--text-secondary);">Active Context:</span>
<strong id="h2hBaseTokens" style="font-family: var(--font-mono); color: #fff;">0 tokens</strong>
</div>
<div style="display: flex; justify-content: space-between; font-size: 0.8rem; margin-bottom: 0.2rem;">
<span style="color: var(--text-secondary);">KV Cache Memory:</span>
<strong id="h2hBaseMemory" style="font-family: var(--font-mono); color: var(--red);">0.00 MB</strong>
</div>
<div style="display: flex; justify-content: space-between; font-size: 0.8rem; margin-bottom: 0.4rem;">
<span style="color: var(--text-secondary);">Latency per Token:</span>
<strong id="h2hBaseLatency" style="font-family: var(--font-mono); color: var(--red);">-- ms</strong>
</div>
<div style="background: rgba(0,0,0,0.5); border-radius: 4px; height: 10px; overflow: hidden; border: 1px solid rgba(255,51,102,0.2);">
<div id="h2hBaseBar" style="background: linear-gradient(90deg, #ff9900, #ff3366); height: 100%; width: 0%; transition: width 0.3s ease;"></div>
</div>
</div>
<div id="h2hBaseAlert" style="font-size: 0.78rem; padding: 0.5rem; background: rgba(0,0,0,0.4); border-radius: 6px; color: var(--text-muted); min-height: 2.2rem;">
Ready to run benchmark.
</div>
</div>
</div>
<!-- Model B: Kalpana RIF Qwen (O(1) Dynamic Cache) -->
<div style="background: rgba(0, 255, 136, 0.04); border: 1px solid rgba(0, 255, 136, 0.3); border-radius: 10px; padding: 1.2rem;">
<div style="display: flex; justify-content: space-between; align-items: center; margin-bottom: 0.8rem;">
<span style="font-weight: 700; color: var(--green); font-size: 0.95rem;">โก Kalpana RIF Qwen (DynamicCache)</span>
<span class="status-tag tag-pass" id="kalpanaStatusTag">O(1) Invariant</span>
</div>
<div style="font-size: 0.8rem; color: var(--text-muted); margin-bottom: 1rem;">
Wave interference: <code>KalpanaCacheLayer.write()</code> across all 24 layers.
</div>
<div style="display: flex; flex-direction: column; gap: 0.7rem;">
<div>
<div style="display: flex; justify-content: space-between; font-size: 0.8rem; margin-bottom: 0.2rem;">
<span style="color: var(--text-secondary);">Active Context:</span>
<strong id="h2hKalpTokens" style="font-family: var(--font-mono); color: #fff;">0 tokens</strong>
</div>
<div style="display: flex; justify-content: space-between; font-size: 0.8rem; margin-bottom: 0.2rem;">
<span style="color: var(--text-secondary);">KV Cache Memory:</span>
<strong id="h2hKalpMemory" style="font-family: var(--font-mono); color: var(--green);">96.00 MB (Strict O(1))</strong>
</div>
<div style="display: flex; justify-content: space-between; font-size: 0.8rem; margin-bottom: 0.4rem;">
<span style="color: var(--text-secondary);">Latency per Token:</span>
<strong id="h2hKalpLatency" style="font-family: var(--font-mono); color: var(--green);">-- ms</strong>
</div>
<div style="background: rgba(0,0,0,0.5); border-radius: 4px; height: 10px; overflow: hidden; border: 1px solid rgba(0,255,136,0.2);">
<div id="h2hKalpBar" style="background: linear-gradient(90deg, #00f0ff, #00ff88); height: 100%; width: 5%; transition: width 0.3s ease;"></div>
</div>
</div>
<div id="h2hKalpAlert" style="font-size: 0.78rem; padding: 0.5rem; background: rgba(0,0,0,0.4); border-radius: 6px; color: var(--green); min-height: 2.2rem;">
Ready to run benchmark.
</div>
</div>
</div>
</div>
</div>
<!-- Memory Scaling Comparison Table -->
<div class="content-card" style="margin-top: 1.5rem;">
<div class="card-head">
<h3>๐ Memory Scaling Comparison: Standard Linear KV Cache vs. Kalpana RIF</h3>
</div>
<table class="data-table">
<thead>
<tr>
<th>Context Horizon</th>
<th>Standard KV Cache (Qwen2.5 / Llama-3)</th>
<th>Kalpana RIF (O(1))</th>
<th>Memory Reduction</th>
<th>Status on Single GPU</th>
</tr>
</thead>
<tbody>
<tr>
<td><strong>2,000 tokens</strong></td>
<td>256 MB</td>
<td><strong class="val-good">96.00 MB</strong></td>
<td>2.7ร smaller</td>
<td><span class="tag-pass">Fits</span></td>
</tr>
<tr>
<td><strong>8,000 tokens</strong></td>
<td>1,024 MB (1.0 GB)</td>
<td><strong class="val-good">96.00 MB</strong></td>
<td>10.6ร smaller</td>
<td><span class="tag-pass">Fits</span></td>
</tr>
<tr>
<td><strong>32,000 tokens</strong></td>
<td>4,096 MB (4.0 GB)</td>
<td><strong class="val-good">96.00 MB</strong></td>
<td>42.6ร smaller</td>
<td><span class="tag-pass">Fits</span></td>
</tr>
<tr>
<td><strong>128,000 tokens</strong></td>
<td>16,384 MB (16.0 GB)</td>
<td><strong class="val-good">96.00 MB</strong></td>
<td>170ร smaller</td>
<td><span class="tag-warn">High VRAM Strain</span></td>
</tr>
<tr>
<td><strong>1,000,000 tokens</strong></td>
<td>138,000 MB (138 GB)</td>
<td><strong class="val-good">96.00 MB</strong></td>
<td><strong>1,437ร smaller</strong></td>
<td><span class="tag-fail">โ Out Of Memory (OOM)</span></td>
</tr>
<tr>
<td><strong>3,000,000 tokens</strong></td>
<td>384,000 MB (384 GB)</td>
<td><strong class="val-good">96.00 MB</strong></td>
<td><strong>4,000ร smaller</strong></td>
<td><span class="tag-fail">โ Needs 5ร A100 GPUs</span></td>
</tr>
</tbody>
</table>
</div>
</div>
</section>
<!-- ============================================================ -->
<!-- TAB 3: LAYER ARCHITECTURE & LLM INTERCEPTION -->
<!-- ============================================================ -->
<section class="tab-pane" id="tab-architecture">
<div class="pane-inner">
<div class="section-header">
<h2>๐๏ธ Deep LLM Layer Architecture: Where RIF Intercepts Attention</h2>
<p>How Kalpana replaces unbounded tensor concatenation (`torch.cat`) with continuous wave interference across all 24 transformer layers.</p>
</div>
<!-- Architecture Visual Diagram -->
<div class="content-card">
<div class="card-head">
<h3>๐ Full Transformer Attention Interception Diagram</h3>
</div>
<div class="diagram-container">
<div class="diagram-block block-input">
<div class="block-title">1. Input Text & Token Embeddings</div>
<div class="block-desc">User prompt text is converted into high-dimensional semantic token embeddings.</div>
</div>
<div class="diagram-arrow">โผ</div>
<div class="diagram-block block-transformer">
<div class="block-title">2. Transformer Hidden Layer Stack (Layers 00 to 23)</div>
<div class="block-desc">Multi-Head Self Attention processes Queries, Keys, and Values across all 24 transformer layers.</div>
<!-- Inner Interception Layer -->
<div class="rif-interception-box">
<div class="interception-badge">โก KALPANA RIF CACHE LAYER (Drop-in Replacement for DynamicCache)</div>
<div class="interception-grid">
<div class="sub-block">
<strong>Standard Transformers:</strong>
<code>torch.cat([Previous_Cache, New_Key_Tokens], dim=-2)</code>
<span class="val-rose">โ Unbounded Linear Memory Growth</span>
</div>
<div class="sub-block">
<strong>Kalpana RIF Substrate:</strong>
<code>KalpanaCacheLayer(past_key_values)</code>
<span class="val-emerald">โ
Constant 96 MB Memory Across All 24 Layers</span>
</div>
</div>
</div>
</div>
<div class="diagram-arrow">โผ</div>
<div class="diagram-block block-sweep">
<div class="block-title">3. Continuous Wave Reconstruction & Attention Synthesis</div>
<div class="block-desc">
Continuous wave memory channels deterministically reconstruct Key and Value attention states with zero memory expansion.
</div>
</div>
<div class="diagram-arrow">โผ</div>
<div class="diagram-block block-output">
<div class="block-title">4. Autoregressive Output Token Generation</div>
<div class="block-desc">Generates response tokens with instant recall and zero recomputation overhead.</div>
</div>
</div>
</div>
<!-- End-to-End System Architecture Flow Card -->
<div class="content-card" style="margin-top: 1.5rem;">
<div class="card-head">
<h3>๐ End-to-End System Architecture & Dataflow Diagram</h3>
</div>
<div style="background: #080c18; border: 1px solid var(--border); border-radius: 8px; padding: 1.5rem; text-align: center;">
<img src="https://raw.githubusercontent.com/maduperera/Kalpana-EmbedToKV/main/assets/kalpana_architecture.png" alt="Kalpana System Architecture Flow" style="max-width: 100%; max-height: 620px; object-fit: contain; border-radius: 6px; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5); background: #ffffff; padding: 12px;">
<div style="font-size: 0.85rem; color: var(--text-muted); margin-top: 1rem; line-height: 1.5;">
Complete pipeline: <strong>User Prompt</strong> โ <strong>Tokenizer</strong> โ <strong>Transformer Hidden Stack (24 Layers)</strong> โ <strong>KalpanaDynamicCache (O(1))</strong> โ <strong>Softmax Attention</strong> โ <strong>Decoded Output</strong>.
</div>
</div>
</div>
</div>
</section>
<!-- ============================================================ -->
<!-- TAB 4: SWAGGER / REST API DOCUMENTATION -->
<!-- ============================================================ -->
<section class="tab-pane" id="tab-swagger">
<div class="pane-inner">
<div class="section-header" style="display: flex; justify-content: space-between; align-items: center; flex-wrap: wrap; gap: 1rem;">
<div>
<h2>๐ Developer OpenAPI / Swagger API Reference</h2>
<p>Standard REST inference and telemetry endpoints powered by dedicated NVIDIA GPU.</p>
</div>
<a href="https://huggingface.co/spaces/MaduRox/Kalpana-API-GPU" target="_blank" class="btn-primary" style="text-decoration: none; width: auto; padding: 0.6rem 1.2rem; display: inline-flex; align-items: center; gap: 0.5rem;">
<span>๐ Open Kalpanฤ GPU Space โ๏ธ</span>
</a>
</div>
<!-- Base URL Banner -->
<div style="background: rgba(0, 240, 255, 0.05); border: 1px solid var(--border-cyan); border-radius: 8px; padding: 0.8rem 1.2rem; margin-bottom: 1.5rem; display: flex; justify-content: space-between; align-items: center;">
<div>
<span style="color: var(--text-muted); font-size: 0.8rem;">HOSTED GPU ENDPOINT:</span>
<span style="font-family: var(--font-mono); font-weight: 700; color: var(--cyan); margin-left: 0.5rem;">https://madurox-kalpana-api-gpu.hf.space</span>
</div>
<span class="status-tag tag-pass">ONLINE ยท NVIDIA GPU (T4 DEDICATED)</span>
</div>
<!-- Windows PowerShell Example -->
<div class="swagger-endpoint open">
<div class="endpoint-header" onclick="toggleSwagger(this)">
<span class="http-method method-post">POWERSHELL</span>
<span class="endpoint-path">Windows PowerShell (Single-Command)</span>
<span class="endpoint-summary">1-Click Execution using native Invoke-RestMethod</span>
<span class="expand-icon">โผ</span>
</div>
<div class="endpoint-body">
<pre class="code-block"><code>$res = Invoke-RestMethod -Uri "https://madurox-kalpana-api-gpu.hf.space/gradio_api/call/generate" -Method Post -ContentType "application/json" -Body '{"data": ["What is cricket?", 128, 0.7]}'
Invoke-RestMethod -Uri "https://madurox-kalpana-api-gpu.hf.space/gradio_api/call/generate/$($res.event_id)"</code></pre>
</div>
</div>
<!-- Python Requests Example -->
<div class="swagger-endpoint">
<div class="endpoint-header" onclick="toggleSwagger(this)">
<span class="http-method method-post">PYTHON</span>
<span class="endpoint-path">Python (requests REST Stream)</span>
<span class="endpoint-summary">Universal 2-step REST streaming client</span>
<span class="expand-icon">โผ</span>
</div>
<div class="endpoint-body">
<pre class="code-block"><code>import requests
# Step 1: Submit prompt
post_res = requests.post(
"https://madurox-kalpana-api-gpu.hf.space/gradio_api/call/generate",
json={"data": ["What is cricket?", 128, 0.7]}
)
event_id = post_res.json()["event_id"]
# Step 2: Stream response
sse_res = requests.get(f"https://madurox-kalpana-api-gpu.hf.space/gradio_api/call/generate/{event_id}")
for line in sse_res.text.split("\n"):
if line.startswith("data:"):
print("Generated Output:", line[5:])</code></pre>
</div>
</div>
<!-- JavaScript Example -->
<div class="swagger-endpoint">
<div class="endpoint-header" onclick="toggleSwagger(this)">
<span class="http-method method-post">JS / WEB</span>
<span class="endpoint-path">JavaScript (fetch SSE Stream)</span>
<span class="endpoint-summary">Web and mobile app client integration</span>
<span class="expand-icon">โผ</span>
</div>
<div class="endpoint-body">
<pre class="code-block"><code>// Step 1: POST prompt
const postRes = await fetch("https://madurox-kalpana-api-gpu.hf.space/gradio_api/call/generate", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ data: ["What is quantum superposition?", 128, 0.7] })
});
const { event_id } = await postRes.json();
// Step 2: Stream answer
const sseRes = await fetch(`https://madurox-kalpana-api-gpu.hf.space/gradio_api/call/generate/${event_id}`);
const text = await sseRes.text();
console.log("Output:", text);</code></pre>
</div>
</div>
</div>
</section>
<!-- ============================================================ -->
<!-- TAB 5: UNIT ECONOMICS & INVESTOR METRICS -->
<!-- ============================================================ -->
<section class="tab-pane" id="tab-economics">
<div class="pane-inner">
<div class="section-header">
<h2>๐ฐ Unit Economics: 800+ Concurrent 1M-Token Contexts on 1 GPU</h2>
<p>How Kalpana eliminates the $432/user/month KV Cache "GPU Tax" down to $2.75/user/month.</p>
</div>
<div class="stats-banner">
<div class="stat-box">
<div class="stat-number val-good">$2.75</div>
<div class="stat-label">Cost per User / Month (1M Context)</div>
</div>
<div class="stat-box">
<div class="stat-number">76.8 GB</div>
<div class="stat-label">VRAM for 800 ร 1M-Token Sessions</div>
</div>
<div class="stat-box">
<div class="stat-number val-rose">110.4 TB</div>
<div class="stat-label">Traditional VRAM Needed for 800 Users</div>
</div>
<div class="stat-box">
<div class="stat-number val-cyan">1,437ร</div>
<div class="stat-label">VRAM Density Multiplication</div>
</div>
</div>
<div class="content-card" style="margin-top: 1.5rem;">
<div class="card-head">
<h3>๐ต Traditional KV-Cache Cost Wall vs. Kalpana RIF ($/user/month)</h3>
</div>
<table class="data-table">
<thead>
<tr>
<th>Context Length</th>
<th>Traditional Cloud API Cost / User / Mo</th>
<th>Kalpana RIF Substrate Cost / User / Mo</th>
<th>Monthly Savings</th>
</tr>
</thead>
<tbody>
<tr>
<td><strong>2,000 tokens</strong></td>
<td>$7.45 / user</td>
<td><strong class="val-good">$2.75 / user</strong></td>
<td>2.7ร cheaper</td>
</tr>
<tr>
<td><strong>8,000 tokens</strong></td>
<td>$28.80 / user</td>
<td><strong class="val-good">$2.75 / user</strong></td>
<td>10.5ร cheaper</td>
</tr>
<tr>
<td><strong>32,000 tokens</strong></td>
<td>$114.00 / user</td>
<td><strong class="val-good">$2.75 / user</strong></td>
<td>41.5ร cheaper</td>
</tr>
<tr>
<td><strong>128,000 tokens</strong></td>
<td>$432.00 / user</td>
<td><strong class="val-good">$2.75 / user</strong></td>
<td>157ร cheaper</td>
</tr>
<tr>
<td><strong>1,000,000 tokens</strong></td>
<td><span class="val-rose">โ (Impractical - $10,000+)</span></td>
<td><strong class="val-good">$2.75 / user</strong></td>
<td><strong>3,600ร cheaper</strong></td>
</tr>
</tbody>
</table>
</div>
</div>
</section>
</div>
</div>
<script type="module" src="./app.js"></script>
</body>
</html>
|